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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names, likely from a sports or news context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    assetsadobe
    -0.84
     constitu
    -0.75
     ende
    -0.70
    etheless
    -0.68
     ����
    -0.67
     exting
    -0.67
     tremend
    -0.66
    Ô
    -0.66
     destro
    -0.64
    PLA
    -0.64
    POSITIVE LOGITS
    esley
    0.75
    chin
    0.74
    hot
    0.71
    hardt
    0.71
    apply
    0.69
    bury
    0.68
    limits
    0.68
    ner
    0.67
    gger
    0.67
    nes
    0.66
    Act Density 0.136%

    No Known Activations