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

    Neuronpedia

    INDEX
    Explanations

    specific dates

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" across the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĢº
    -0.59
     distinguishes
    -0.56
     illustrates
    -0.55
    leeve
    -0.55
     seems
    -0.55
    itars
    -0.55
    anova
    -0.55
     partName
    -0.54
    !
    -0.54
     because
    -0.54
    POSITIVE LOGITS
     latter
    1.06
     aforementioned
    1.05
     same
    1.03
     slightest
    1.01
     remainder
    0.98
     entirety
    0.91
     entire
    0.86
     ensuing
    0.85
     respective
    0.84
     requisite
    0.83
    Act Density 0.994%

    No Known Activations