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

    Neuronpedia

    INDEX
    Explanations

    phrases related to contrasting or delineating points

    oai_token-act-pair · gpt-3.5-turbo

    clauses or phrases that emphasize contrasts or contradictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iffe
    -0.67
    eni
    -0.67
    IER
    -0.65
    VIS
    -0.64
     Became
    -0.62
    hurst
    -0.61
    aky
    -0.61
    USS
    -0.60
    RESULTS
    -0.60
    uman
    -0.59
    POSITIVE LOGITS
     nor
    1.78
    nor
    1.38
     anymore
    1.09
     Nor
    1.05
    although
    1.02
     but
    1.02
     though
    0.97
     Rather
    0.96
     although
    0.95
     merely
    0.94
    Act Density 0.147%

    No Known Activations