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

    Neuronpedia

    INDEX
    Explanations

    brand names

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that are empty or contain specific formatting without meaningful content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    henko
    -0.67
    lla
    -0.65
    cano
    -0.64
    lished
    -0.62
    coni
    -0.61
    IRO
    -0.60
    recated
    -0.60
     cx
    -0.59
    itals
    -0.59
    lli
    -0.59
    POSITIVE LOGITS
    igans
    1.27
    ittle
    1.11
    igan
    1.07
    abies
    0.99
    enburg
    0.98
    ibrary
    0.96
    ounge
    0.96
    igible
    0.94
    isted
    0.91
    abor
    0.90
    Act Density 0.083%

    No Known Activations