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

    Neuronpedia

    INDEX
    Explanations

    ambiguous and enigmatic phrases

    oai_token-act-pair · gpt-3.5-turbo

    articles preceding nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adj
    -0.91
    grounds
    -0.82
    evidence
    -0.75
     Industries
    -0.75
    onto
    -0.72
    mite
    -0.72
    Things
    -0.69
    aniel
    -0.69
    encies
    -0.68
    here
    -0.68
    POSITIVE LOGITS
     bang
    1.06
     bunch
    1.04
     handful
    0.99
     vengeance
    0.99
     plethora
    0.98
     few
    0.92
     multitude
    0.90
     smile
    0.88
     penchant
    0.88
     caveat
    0.87
    Act Density 0.142%

    No Known Activations