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

    Neuronpedia

    INDEX
    Explanations

    numeric values followed by units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numerical values or rates, especially in relation to quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nod
    -0.77
     nods
    -0.76
     notices
    -0.72
     Dahl
    -0.71
     Xer
    -0.70
     Shade
    -0.69
     Edgar
    -0.68
     sooner
    -0.68
     smells
    -0.67
     indications
    -0.67
    POSITIVE LOGITS
    each
    1.12
    etc
    1.10
    AU
    1.06
    hr
    1.02
    Hour
    1.01
    whatever
    0.98
    hour
    0.98
    grad
    0.98
    oct
    0.97
    month
    0.97
    Act Density 0.026%

    No Known Activations