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

    Neuronpedia

    INDEX
    Explanations

    numbers and abbreviations in sentences

    oai_token-act-pair · gpt-3.5-turbo

    periods in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AUD
    -0.70
     guiActiveUn
    -0.68
    ichick
    -0.66
    idem
    -0.64
    Reviewed
    -0.63
    fml
    -0.61
    Shape
    -0.61
     econom
    -0.60
     rhy
    -0.60
     authent
    -0.59
    POSITIVE LOGITS
     Eliot
    0.74
    A
    0.70
    O
    0.66
     Agency
    0.65
     Leone
    0.64
     Kear
    0.63
    dylib
    0.63
     Lover
    0.63
     Kills
    0.63
     Dreams
    0.62
    Act Density 0.054%

    No Known Activations