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

    Neuronpedia

    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotes or dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rul
    -0.92
     sucker
    -0.90
     glac
    -0.88
     knockout
    -0.88
     favor
    -0.86
     knack
    -0.83
     crunch
    -0.83
     blitz
    -0.82
     quir
    -0.82
     creep
    -0.81
    POSITIVE LOGITS
    Our
    1.93
    Due
    1.83
    While
    1.83
    We
    1.81
    Given
    1.81
    Following
    1.79
    Although
    1.77
    Despite
    1.76
    Effective
    1.76
    Based
    1.74
    Act Density 0.186%

    No Known Activations