© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 871
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical elements and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aque
    -0.76
    aura
    -0.76
    vous
    -0.74
    ventures
    -0.71
    auga
    -0.71
    oward
    -0.69
     contempl
    -0.68
    leon
    -0.68
     corrid
    -0.66
    oma
    -0.65
    POSITIVE LOGITS
     PVC
    0.74
     gold
    0.69
     plutonium
    0.68
    elsen
    0.67
     petroleum
    0.67
     Javascript
    0.66
     SOFTWARE
    0.65
     Firearms
    0.65
     timber
    0.65
     TNT
    0.65
    Activations Density 0.177%

    No Known Activations