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

    Neuronpedia

    INDEX
    Explanations

    statements of certainty or assurance

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "there's no" and its variations, indicating a negation or absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ean
    -0.76
    late
    -0.74
    aug
    -0.72
    romeda
    -0.71
    onduct
    -0.70
    NF
    -0.69
    atl
    -0.69
    lish
    -0.68
    cheon
    -0.68
    eds
    -0.67
    POSITIVE LOGITS
     doubt
    1.32
     denying
    1.27
     shortage
    1.27
     excuse
    1.23
     reason
    1.16
     contradiction
    1.09
     shame
    1.09
     downside
    1.07
     question
    1.06
     justification
    1.02
    Act Density 0.066%

    No Known Activations