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

    Neuronpedia

    INDEX
    Explanations

    plural noun phrases indicating groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to different groups of people and their characteristics or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺ
    -0.75
    friend
    -0.70
    gy
    -0.69
    thood
    -0.64
    ĵ
    -0.63
    ķ
    -0.60
    gyn
    -0.60
    busters
    -0.59
    gil
    -0.59
    ison
    -0.58
    POSITIVE LOGITS
     lurking
    0.76
     somew
    0.68
    abouts
    0.68
     hiding
    0.68
     overlap
    0.68
     circulating
    0.65
     mismatch
    0.65
    othal
    0.65
     waiting
    0.64
     ripple
    0.63
    Act Density 0.355%

    No Known Activations