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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions or classifications

    oai_token-act-pair · gpt-3.5-turbo

    instances where the word "technically" is used

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieties
    -0.69
    velt
    -0.69
     Cities
    -0.67
     Neighbor
    -0.65
    cot
    -0.65
    vic
    -0.63
     Hungry
    -0.62
    orf
    -0.61
    vation
    -0.61
     Vaj
    -0.61
    POSITIVE LOGITS
     inclined
    0.88
     speaking
    0.88
     minded
    0.81
     correct
    0.76
     incorrect
    0.75
     proficient
    0.74
    ename
    0.73
     inaccurate
    0.69
     illiter
    0.69
     inept
    0.67
    Act Density 0.021%

    No Known Activations