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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "manually" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to manual actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soon
    -0.73
    ĸļ
    -0.71
     Kerry
    -0.71
    riots
    -0.70
    rug
    -0.67
    Magikarp
    -0.66
    addons
    -0.66
    rus
    -0.66
    dar
    -0.66
     Coverage
    -0.65
    POSITIVE LOGITS
     manually
    0.90
     bleed
    0.86
     exting
    0.85
     override
    0.82
     calibr
    0.81
     overcl
    0.79
     eleph
    0.78
     configured
    0.78
     induct
    0.78
     synchron
    0.77
    Act Density 0.009%

    No Known Activations