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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or transformations performed on objects

    oai_token-act-pair · gpt-3.5-turbo

    past participle forms of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antage
    -0.68
    cially
    -0.65
    Nap
    -0.64
    rir
    -0.64
    cial
    -0.63
    bang
    -0.61
    adra
    -0.59
    sit
    -0.58
     occupancy
    -0.57
    actual
    -0.57
    POSITIVE LOGITS
     by
    1.04
     BY
    0.83
    ĸļ
    0.80
    abouts
    0.79
     anew
    0.78
     aback
    0.77
     Parenthood
    0.75
     merciless
    0.74
    uled
    0.74
     differently
    0.72
    Act Density 0.120%

    No Known Activations