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

    Neuronpedia

    INDEX
    Explanations

    indicative verbs and phrases suggesting causation or future actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     تانيه
    -0.61
    ificação
    -0.55
    руя
    -0.53
    *)((
    -0.52
    cshtml
    -0.52
    脚注の使い方
    -0.52
     pungkasnya
    -0.52
    freies
    -0.51
    brü
    -0.51
    loroethane
    -0.49
    POSITIVE LOGITS
    expandindo
    0.84
     فريبيس
    0.73
    AsUp
    0.73
    kloped
    0.73
    complexContent
    0.65
     anybody
    0.64
     TestBed
    0.63
     ویکی‌پدی
    0.62
    >*/
    0.60
     beginnetje
    0.60
    Act Density 0.113%

    No Known Activations