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

    Neuronpedia

    INDEX
    Explanations

    names that end with the letter 'y'

    oai_token-act-pair · gpt-3.5-turbo

    individual letters or symbols frequently occurring in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.76
    姫
    -0.76
     absor
    -0.68
    BALL
    -0.67
     tremend
    -0.66
    Magikarp
    -0.63
     toget
    -0.63
     shutter
    -0.63
     clutch
    -0.62
     almonds
    -0.62
    POSITIVE LOGITS
    MN
    0.82
    \-
    0.80
    adic
    0.79
    Va
    0.78
    Gs
    0.78
    ama
    0.76
    Bi
    0.73
    ul
    0.73
    û
    0.73
    uter
    0.72
    Act Density 0.197%

    No Known Activations