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

    Neuronpedia

    INDEX
    Explanations

    words indicating hypotheses or suggestions based on scientific evidence

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Roskov
    -0.84
     '\\;'
    -0.79
     Shakspeare
    -0.78
     myſelf
    -0.78
     Thine
    -0.73
     Shaksp
    -0.73
     photolibrary
    -0.73
    évaluateur
    -0.73
    writeFieldEnd
    -0.72
     chofe
    -0.71
    POSITIVE LOGITS
     a
    0.59
    üm
    0.52
    .
    0.51
     men
    0.49
     Metzger
    0.49
     Z
    0.49
    enumi
    0.49
    FormField
    0.49
    ige
    0.48
    PLEMENT
    0.48
    Act Density 0.013%

    No Known Activations