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

    Neuronpedia

    INDEX
    Explanations

    mentions of individual names or specific events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     scattering
    -0.79
     variance
    -0.71
     infringing
    -0.70
    ensical
    -0.67
     dividing
    -0.67
     Downs
    -0.65
     tremend
    -0.65
     handshake
    -0.65
     shack
    -0.62
     giveaways
    -0.61
    POSITIVE LOGITS
    ¹
    1.12
    £
    1.07
    Į
    0.98
    ¬
    0.97
    ı
    0.96
    º
    0.94
    ħ
    0.93
    Ń
    0.90
    ¸
    0.89
    ²
    0.89
    Act Density 0.263%

    No Known Activations