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

    Neuronpedia

    INDEX
    Explanations

    comparisons or contrasts between different scenarios or situations

    oai_token-act-pair · gpt-3.5-turbo

    comparisons highlighting the phrase "as ... as"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irin
    -0.71
    WIND
    -0.62
     Advertisement
    -0.62
    wa
    -0.59
    Winged
    -0.58
     Ident
    -0.58
     Beginning
    -0.58
     Telecommunications
    -0.58
    SourceFile
    -0.57
    igh
    -0.56
    POSITIVE LOGITS
     usual
    1.06
     advertised
    0.90
     hoped
    0.90
    usual
    0.89
    expected
    0.83
    ptions
    0.80
     envisioned
    0.79
     promised
    0.79
     feared
    0.78
     customary
    0.77
    Act Density 0.261%

    No Known Activations