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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers with periods in between

    oai_token-act-pair · gpt-3.5-turbo

    sequences related to specific technical versions and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.82
    enhagen
    -0.68
    anchester
    -0.68
     Howe
    -0.66
     showc
    -0.65
     Dirk
    -0.63
     Medina
    -0.62
    cest
    -0.60
    cius
    -0.59
     glances
    -0.58
    POSITIVE LOGITS
    fif
    0.88
    poons
    0.80
    Ïī
    0.75
    oshenko
    0.70
    ongyang
    0.68
    teen
    0.68
    bp
    0.67
    \-
    0.67
    obl
    0.66
    gm
    0.65
    Act Density 0.174%

    No Known Activations