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

    Neuronpedia

    INDEX
    Explanations

    numerical values or fractions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    WireFormat
    -0.72
     Schrö
    -0.65
    providedIn
    -0.63
    ApiOperation
    -0.63
     smtplib
    -0.62
    FieldDescriptor
    -0.62
    PRNewswire
    -0.60
     Schwe
    -0.59
    igshid
    -0.59
    LogFactory
    -0.59
    POSITIVE LOGITS
     survie
    0.81
    encils
    0.78
    othesis
    0.77
    zeitig
    0.74
    sschule
    0.73
    جراء
    0.73
    ½
    0.73
     materialen
    0.72
     myſelf
    0.72
     Tudor
    0.71
    Act Density 0.001%

    No Known Activations