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

    Neuronpedia

    INDEX
    Explanations

    descriptions of and references to advertisements

    oai_token-act-pair · gpt-3.5-turbo

    references to advertisements and manuscripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.99
    ré
    -0.86
    ers
    -0.80
    guy
    -0.77
    lot
    -0.76
    ones
    -0.76
    orb
    -0.75
    arer
    -0.75
    ersen
    -0.74
    men
    -0.73
    POSITIVE LOGITS
     mosqu
    0.75
    igslist
    0.72
     ransom
    0.71
    furt
    0.65
     burner
    0.64
    culosis
    0.64
    =~=~
    0.61
    bilt
    0.61
    ciating
    0.60
     envelope
    0.59
    Act Density 0.045%

    No Known Activations