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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abit
    -0.69
     Myth
    -0.67
     Diff
    -0.64
     filibuster
    -0.62
     Pist
    -0.61
     Mush
    -0.60
    earable
    -0.59
     obs
    -0.58
     bang
    -0.57
     Shu
    -0.56
    POSITIVE LOGITS
    itri
    0.80
    xual
    0.72
    apters
    0.71
    rals
    0.71
    urion
    0.69
    redits
    0.67
    icularly
    0.66
    entious
    0.66
    urs
    0.66
    ording
    0.66
    Act Density 0.134%

    No Known Activations