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

    Neuronpedia

    INDEX
    Explanations

    percentages or proportions mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    numeric expressions and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phasis
    -0.64
    leted
    -0.64
    lance
    -0.63
    multipl
    -0.63
    alam
    -0.62
     Plague
    -0.62
    tre
    -0.61
    gran
    -0.60
     reborn
    -0.60
    overty
    -0.60
    POSITIVE LOGITS
     anymore
    0.77
    eenth
    0.76
    iffe
    0.70
     cents
    0.69
     spots
    0.67
     Eag
    0.66
    ever
    0.66
     percent
    0.65
     hours
    0.63
     weeks
    0.63
    Act Density 0.089%

    No Known Activations