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

    Neuronpedia

    INDEX
    Explanations

    words related to additives and their roles or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    added
    -0.20
    IOUS
    -0.18
    _BS
    -0.16
    coni
    -0.15
    panic
    -0.15
    üp
    -0.15
    anness
    -0.15
    vey
    -0.15
    EGA
    -0.15
    egis
    -0.15
    POSITIVE LOGITS
    ison
    0.29
    endum
    0.28
    uctor
    0.24
    itions
    0.24
    enda
    0.24
    tl
    0.23
    iction
    0.23
    er
    0.23
    ictions
    0.23
    itive
    0.23
    Act Density 0.015%

    No Known Activations