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

    Neuronpedia

    INDEX
    Explanations

    expressions related to experiences, choices, and personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iren
    -0.16
     Kenn
    -0.15
    Lon
    -0.14
    hod
    -0.14
     Lon
    -0.14
    OMP
    -0.14
    maj
    -0.14
    ³
    -0.14
    407
    -0.13
     hoa
    -0.13
    POSITIVE LOGITS
    /rfc
    0.17
     guint
    0.15
    _PK
    0.15
    contr
    0.15
    erland
    0.14
    osto
    0.14
    athers
    0.14
    HING
    0.14
    ansen
    0.14
    arena
    0.14
    Act Density 0.112%

    No Known Activations