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

    Neuronpedia

    INDEX
    Explanations

    dates or month names within the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    jspx
    -0.63
    itm
    -0.62
     díl
    -0.57
    rosa
    -0.56
    ersburg
    -0.56
    labelText
    -0.56
     September
    -0.56
    cosx
    -0.54
    oneofs
    -0.53
     His
    -0.53
    POSITIVE LOGITS
     ſever
    1.16
     pleaſure
    1.15
     raiſ
    1.14
     juſ
    1.13
     miſ
    1.08
     ſeveral
    1.08
     faſt
    1.07
     ſtill
    1.05
     Diſ
    1.03
     Majefty
    1.03
    Act Density 0.009%

    No Known Activations