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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the usage or application of a tool, technique, or strategy

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "use" and "used", indicating a focus on actions or activities involving application or implementation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     4090
    -0.62
     Hai
    -0.62
     Ascend
    -0.60
    progress
    -0.60
    bda
    -0.59
    llah
    -0.59
    rats
    -0.58
    nesty
    -0.57
     issu
    -0.56
     undertaking
    -0.56
    POSITIVE LOGITS
    fully
    1.15
    FUL
    0.91
     sparing
    0.91
     leverage
    0.90
     phrases
    0.86
    nels
    0.78
     tricks
    0.77
    illin
    0.76
     discretion
    0.76
     condoms
    0.75
    Act Density 0.133%

    No Known Activations