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

    Neuronpedia

    INDEX
    Explanations

    instances of quote marks, particularly those related to speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawDesc
    -0.59
     שוליים
    -0.53
    っきり
    -0.47
    sidemargin
    -0.46
    ellido
    -0.46
     архивлан
    -0.45
    LookAnd
    -0.45
    尔斯
    -0.45
     SqlParameter
    -0.44
    JsonHelper
    -0.44
    POSITIVE LOGITS
    twas
    0.82
    nuff
    0.77
    bout
    0.76
    Twas
    0.74
    cause
    0.73
    til
    0.72
    fraid
    0.71
    em
    0.71
    nother
    0.70
    tween
    0.67
    Act Density 0.245%

    No Known Activations