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

    Neuronpedia

    INDEX
    Explanations

    example codes and software-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "example."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensibly
    -0.85
    ternity
    -0.82
    reditary
    -0.79
     mathemat
    -0.75
    ole
    -0.75
    resent
    -0.74
    emetery
    -0.72
    burgh
    -0.72
    ishops
    -0.70
    ecided
    -0.70
    POSITIVE LOGITS
     illustrating
    0.97
     subp
    0.96
     thereof
    0.74
     sentences
    0.73
    hetical
    0.70
     demonstrating
    0.69
     below
    0.68
    icles
    0.68
    wcsstore
    0.66
     sketch
    0.65
    Act Density 0.058%

    No Known Activations