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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 571
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to individuals or entities

    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
    ��
    -0.97
    �
    -0.83
    �
    -0.82
    orian
    -0.82
    �
    -0.81
    rib
    -0.80
    oğ
    -0.78
    vell
    -0.77
    �
    -0.77
    etting
    -0.77
    POSITIVE LOGITS
     happened
    0.67
     son
    0.66
     happens
    0.64
     clip
    0.61
     aspiration
    0.60
     Stead
    0.60
     happen
    0.60
     prediction
    0.59
     unilaterally
    0.58
     Interactive
    0.58
    Activations Density 1.410%

    No Known Activations