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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future actions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.62
    ьаж
    -0.57
    脚注の使い方
    -0.56
     betweenstory
    -0.55
     indisponible
    -0.54
    Fácil
    -0.51
    insee
    -0.50
     vicenda
    -0.50
    Suisse
    -0.49
    EDEFAULT
    -0.49
    POSITIVE LOGITS
     going
    0.83
     gonna
    0.68
     will
    0.58
     ought
    0.55
    going
    0.55
     GOING
    0.54
     supposed
    0.54
    multicolumn
    0.54
     Going
    0.53
     likely
    0.52
    Act Density 0.109%

    No Known Activations