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

    Neuronpedia

    INDEX
    Explanations

    references to "from" indicating a source or origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rug
    -0.16
    unas
    -0.15
    lah
    -0.15
    rome
    -0.15
    acet
    -0.14
    (disposing
    -0.14
    Ñģол
    -0.14
    rias
    -0.14
     footnote
    -0.14
    inger
    -0.13
    POSITIVE LOGITS
    /to
    0.32
     scratch
    0.20
    /by
    0.19
    /about
    0.19
    scratch
    0.17
    /of
    0.16
     vá»±
    0.16
    mel
    0.15
    s
    0.15
    mers
    0.15
    Act Density 0.308%

    No Known Activations