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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    حياته
    -0.90
     vaisselle
    -0.81
    ſelf
    -0.81
    edip
    -0.78
     bandoulière
    -0.78
     Monfieur
    -0.77
     espagne
    -0.76
    pośred
    -0.76
     auffi
    -0.75
     sánchez
    -0.75
    POSITIVE LOGITS
     para
    3.10
    Para
    2.74
     Para
    2.72
    para
    2.60
     PARA
    2.48
    PARA
    2.25
    パラ
    1.23
     пара
    1.20
     parach
    1.17
     paraffin
    1.06
    Act Density 0.021%

    No Known Activations