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

    Neuronpedia

    INDEX
    Explanations

    verbs related to forceful or intense action

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to influence or action within a social or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     narrated
    -0.72
    DragonMagazine
    -0.67
    interrupted
    -0.65
     ·
    -0.63
    ItemThumbnailImage
    -0.60
    kr
    -0.59
     bounded
    -0.57
    AMY
    -0.56
    anse
    -0.56
     located
    -0.56
    POSITIVE LOGITS
     out
    0.73
     away
    0.70
    ILA
    0.69
     down
    0.68
    ħĭ
    0.68
    otom
    0.67
     overboard
    0.67
    irtual
    0.67
     up
    0.67
     forth
    0.66
    Act Density 0.301%

    No Known Activations