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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and functions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.74
    mybatisplus
    -0.63
    profen
    -0.63
    ΗΣ
    -0.63
     Glad
    -0.62
     jegy
    -0.62
    GenerationType
    -0.60
     “
    -0.59
     Stern
    -0.59
    qrstuvwxyz
    -0.59
    POSITIVE LOGITS
     himſelf
    0.86
     themſelves
    0.82
     itſelf
    0.81
     myſelf
    0.80
     Futura
    0.77
     reaſon
    0.76
     poffible
    0.76
     fufficient
    0.75
     Majefty
    0.75
     Efq
    0.75
    Act Density 0.101%

    No Known Activations