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

    Neuronpedia

    INDEX
    Explanations

    percentages mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cra
    -0.69
    bard
    -0.67
    LAN
    -0.67
    aucus
    -0.67
    hub
    -0.66
    chat
    -0.64
    Hub
    -0.63
    achus
    -0.63
    ilater
    -0.63
    arty
    -0.63
    POSITIVE LOGITS
     thousand
    1.17
     percent
    1.05
     cents
    0.99
     hundred
    0.93
    teen
    0.86
     million
    0.83
    een
    0.83
    eenth
    0.82
     pounds
    0.81
    teenth
    0.80
    Act Density 0.036%

    No Known Activations