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

    Neuronpedia

    INDEX
    Explanations

    themes of trust and deception in relationships and narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     projected
    -0.16
     predicted
    -0.15
    olang
    -0.15
     //
    -0.14
    tej
    -0.14
    g
    -0.14
     Burke
    -0.14
    uros
    -0.14
    WR
    -0.13
    ABS
    -0.13
    POSITIVE LOGITS
    dorf
    0.17
    serter
    0.16
    _Generic
    0.15
    nier
    0.14
    æ¢
    0.14
    _GC
    0.14
    еÑĢед
    0.14
    çİī
    0.14
    /rfc
    0.14
    PFN
    0.14
    Act Density 0.192%

    No Known Activations