Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 103
    Prev
    Next
    INDEX
    Explanations

    references to body parts and injuries

    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
     Primordial
    -0.66
     assigned
    -0.59
     switched
    -0.59
     countered
    -0.58
     Ec
    -0.56
    pton
    -0.55
     Marvin
    -0.55
     resident
    -0.55
     fleet
    -0.54
     parked
    -0.54
    POSITIVE LOGITS
    ntil
    0.87
    catentry
    0.85
    aughs
    0.85
    itory
    0.79
    vae
    0.79
    escription
    0.76
    vertisement
    0.72
    Leaks
    0.71
    ��
    0.70
    vironment
    0.70
    Activations Density 0.139%

    No Known Activations