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

    Neuronpedia

    INDEX
    Explanations

    phrases related to active and direct participation or involvement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to participation and involvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geons
    -0.77
    sell
    -0.76
    hest
    -0.73
    geries
    -0.70
    pex
    -0.69
    objects
    -0.68
    geon
    -0.67
    label
    -0.67
    cale
    -0.66
    yre
    -0.66
    POSITIVE LOGITS
    ateral
    0.80
    enza
    0.73
    jriwal
    0.71
     rate
    0.71
     rates
    0.71
    alia
    0.70
    avement
    0.67
    orship
    0.66
     Rate
    0.65
    iscons
    0.65
    Act Density 0.073%

    No Known Activations