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

    Neuronpedia

    INDEX
    Explanations

    negative implications or restrictions indicated by the word "not"

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating exclusions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fail
    -0.64
     Puzz
    -0.62
    itiveness
    -0.60
    HAEL
    -0.59
    _-_
    -0.59
    assetsadobe
    -0.59
    roo
    -0.57
    manship
    -0.57
     underest
    -0.56
    issance
    -0.56
    POSITIVE LOGITS
     necessarily
    1.18
     otherwise
    1.13
     ordinarily
    1.07
     explicitly
    0.99
     yet
    0.99
     normally
    0.95
     expressly
    0.94
     already
    0.86
     traditionally
    0.85
     overtly
    0.83
    Act Density 0.172%

    No Known Activations