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

    Neuronpedia

    INDEX
    Explanations

    statements or quotes from individuals

    oai_token-act-pair · gpt-3.5-turbo

    reported speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arest
    -0.76
    EEE
    -0.75
    asu
    -0.73
    Pont
    -0.73
    Ranked
    -0.72
    folios
    -0.72
    ptives
    -0.72
    estial
    -0.71
    adesh
    -0.71
    astrous
    -0.71
    POSITIVE LOGITS
     goodbye
    0.97
     afterward
    0.85
     hello
    0.80
     angrily
    0.79
     afterwards
    0.78
     anecd
    0.76
     regrets
    0.73
    doms
    0.71
     remorse
    0.69
     confession
    0.69
    Act Density 0.277%

    No Known Activations