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

    Neuronpedia

    INDEX
    Explanations

    symbols or decorative characters

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific character or symbol repeated in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     drills
    -0.67
     jaws
    -0.65
     Stam
    -0.59
     lid
    -0.59
     loopholes
    -0.58
     Crane
    -0.56
     lapse
    -0.56
    interstitial
    -0.56
    achus
    -0.55
    handedly
    -0.55
    POSITIVE LOGITS
    mosp
    0.78
    wait
    0.73
    imaru
    0.72
    weet
    0.70
    Products
    0.70
    come
    0.69
    arate
    0.68
    arro
    0.68
    where
    0.67
    Whereas
    0.67
    Act Density 0.027%

    No Known Activations