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

    Neuronpedia

    INDEX
    Explanations

    specific instances or scenarios related to a general statement or subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize a significant number or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venants
    -0.73
    ledged
    -0.73
    marks
    -0.69
    println
    -0.68
    Domin
    -0.67
    amaru
    -0.66
    onis
    -0.64
    ragon
    -0.62
    pred
    -0.61
    mosp
    -0.58
    POSITIVE LOGITS
     reason
    1.80
     purpose
    1.56
     sake
    1.56
     reasons
    1.45
     purposes
    1.45
     Reason
    1.03
     occasion
    0.99
     Reasons
    0.99
     matter
    0.96
    ummies
    0.85
    Act Density 0.061%

    No Known Activations