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

    Neuronpedia

    INDEX
    Explanations

    personal development phrases and self-improvement concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     substitutes
    -0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.60
     hapl
    -0.59
     dots
    -0.59
     exch
    -0.58
     sar
    -0.58
     largeDownload
    -0.58
     levers
    -0.58
     bribes
    -0.57
     resemb
    -0.56
    POSITIVE LOGITS
    iversary
    0.74
    Episode
    0.73
    movie
    0.72
    Fest
    0.68
    idays
    0.68
    ieth
    0.67
    NFL
    0.66
    conference
    0.66
    league
    0.65
    authorized
    0.63
    Act Density 0.714%

    No Known Activations