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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "plus" along with numerical values or symbols

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    agliari
    -0.58
     acido
    -0.55
     barri
    -0.54
     iman
    -0.54
    ]='\
    -0.54
     kön
    -0.54
     fides
    -0.53
     mariana
    -0.53
     vernac
    -0.52
     محفوظة
    -0.51
    POSITIVE LOGITS
     Plus
    0.98
    Plus
    0.96
     plus
    0.96
    plus
    0.93
     PLUS
    0.88
    PLUS
    0.84
     affez
    0.69
     minus
    0.65
     statunit
    0.63
     prépare
    0.62
    Act Density 0.059%

    No Known Activations