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

    Neuronpedia

    INDEX
    Explanations

    references to chocolate and related flavors

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    cheme
    -0.91
    eczki
    -0.88
     Dmitry
    -0.84
     Menlo
    -0.82
     imageNamed
    -0.81
     (!__
    -0.80
    ofag
    -0.79
     Zayed
    -0.79
     Stanton
    -0.79
    ;*/
    -0.79
    POSITIVE LOGITS
     Cho
    1.34
    Cho
    1.20
    cho
    0.94
     cho
    0.93
     chops
    0.85
     Chop
    0.84
     chop
    0.78
     CHO
    0.74
    OCOLATE
    0.72
    Chop
    0.71
    Act Density 0.005%

    No Known Activations