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

    Neuronpedia

    INDEX
    Explanations

    phrases related to companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    semicolons in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ront
    -0.82
    din
    -0.81
    senal
    -0.81
    orts
    -0.78
    urrection
    -0.74
    rio
    -0.74
    hemer
    -0.71
    izons
    -0.70
    wald
    -0.70
    rons
    -0.69
    POSITIVE LOGITS
     alternatively
    1.00
     furthermore
    0.97
    -)
    0.97
     thence
    0.97
     moreover
    0.88
     consequently
    0.85
     namely
    0.84
     };
    0.82
    anwhile
    0.80
     whereas
    0.79
    Act Density 0.054%

    No Known Activations