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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing a high quantity or degree of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions emphasizing abundance or excess

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ares
    -0.82
    iques
    -0.78
    aves
    -0.78
    hammad
    -0.77
    cles
    -0.77
    ends
    -0.77
    runs
    -0.76
    arts
    -0.74
    asts
    -0.72
    breakers
    -0.70
    POSITIVE LOGITS
     reason
    0.99
     overlap
    0.99
     evidence
    0.98
     misinformation
    0.91
     similarity
    0.91
     difference
    0.90
     possibility
    0.90
     confusion
    0.89
     indication
    0.89
     irony
    0.88
    Act Density 0.113%

    No Known Activations