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

    Neuronpedia

    INDEX
    Explanations

    statements of certainty or high likelihood

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" and their various usages in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Benefits
    -0.79
    idth
    -0.70
     congr
    -0.70
     GOODMAN
    -0.67
    orsi
    -0.67
    ESE
    -0.65
     Extend
    -0.64
    boarding
    -0.64
    sense
    -0.64
    ":[{"
    -0.63
    POSITIVE LOGITS
     unreliable
    1.32
     ineffective
    1.29
     inadequate
    1.29
     incomplete
    1.29
     unable
    1.26
     insufficient
    1.26
     lacking
    1.25
     unlikely
    1.25
     uncertain
    1.22
     inconsistent
    1.17
    Act Density 0.373%

    No Known Activations