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

    Neuronpedia

    INDEX
    Explanations

    dates and specific numbers

    oai_token-act-pair · gpt-3.5-turbo

    specific names, dates, and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IU
    -0.76
    ById
    -0.66
    rir
    -0.65
    xual
    -0.64
    ucl
    -0.63
    addle
    -0.60
     womb
    -0.58
    illions
    -0.58
     è£ıè
    -0.57
     guiActiveUnfocused
    -0.57
    POSITIVE LOGITS
    tein
    0.70
    Å¡
    0.60
     Malf
    0.59
    assi
    0.56
    vous
    0.55
    umbing
    0.55
    ð
    0.54
    Äį
    0.53
    izon
    0.53
    Ń·
    0.53
    Act Density 1.106%

    No Known Activations