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

    Neuronpedia

    INDEX
    Explanations

    mentions or variations of the word "ison"

    oai_token-act-pair · gpt-3.5-turbo

    the character "ison" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astically
    -0.84
    undo
    -0.84
    appers
    -0.81
    uled
    -0.78
    ifter
    -0.77
    estones
    -0.75
    astical
    -0.73
    ulative
    -0.70
    izoph
    -0.70
     therape
    -0.69
    POSITIVE LOGITS
    naire
    0.95
    nette
    0.86
    ette
    0.85
    nect
    0.85
    hof
    0.84
    xual
    0.84
    ça
    0.82
    ettes
    0.81
    eers
    0.76
    ements
    0.76
    Act Density 0.019%

    No Known Activations