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

    Neuronpedia

    INDEX
    Explanations

    references to digital or virtual items, particularly online lists or collections

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    xl
    -0.71
    kháu
    -0.60
     Coleman
    -0.56
     passim
    -0.54
     Jefus
    -0.52
    Personendaten
    -0.52
     Guay
    -0.51
    łosi
    -0.50
    Coleman
    -0.50
     Schlag
    -0.49
    POSITIVE LOGITS
    orption
    1.12
    vh
    0.95
    dled
    0.88
    combin
    0.86
    AMES
    0.82
    dle
    0.81
    ames
    0.77
    AME
    0.73
    VH
    0.73
     صوتيه
    0.68
    Act Density 0.005%

    No Known Activations