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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce examples or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Plenum
    -0.63
     مشين
    -0.62
    unica
    -0.60
    thea
    -0.58
     église
    -0.57
     castelo
    -0.54
     compétence
    -0.53
     ''.
    -0.53
     Portanto
    -0.52
    Mui
    -0.52
    POSITIVE LOGITS
    Например
    0.89
     bijvoorbeeld
    0.84
     Например
    0.83
     exempel
    0.82
     например
    0.82
     example
    0.81
    たとえば
    0.81
     Misalnya
    0.79
     třeba
    0.76
     beispielsweise
    0.76
    Act Density 0.151%

    No Known Activations