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

    Neuronpedia

    INDEX
    Explanations

    parentheses and punctuation in general

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     answ
    -0.71
     usher
    -0.63
     detrim
    -0.60
    bos
    -0.59
     conduc
    -0.58
    NPR
    -0.57
     assum
    -0.57
     viability
    -0.56
     blo
    -0.56
     spo
    -0.56
    POSITIVE LOGITS
    ãĥİ
    0.80
    76561
    0.77
    enic
    0.64
    ucky
    0.64
     Benef
    0.63
     âĵĺ
    0.63
    eneg
    0.63
    ²
    0.62
     Frames
    0.61
    ivo
    0.61
    Act Density 0.044%

    No Known Activations