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

    Neuronpedia

    INDEX
    Explanations

    references to actions or decisions made in succession or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibs
    -0.15
    uro
    -0.15
    ceae
    -0.15
    dia
    -0.14
    onse
    -0.14
    avanaugh
    -0.14
     exactly
    -0.14
    -lfs
    -0.14
    cket
    -0.13
    sel
    -0.13
    POSITIVE LOGITS
    acre
    0.19
    neath
    0.16
    lore
    0.15
    hin
    0.14
    eway
    0.14
    aire
    0.14
    -up
    0.14
    ieve
    0.14
    ings
    0.14
    ores
    0.14
    Act Density 0.028%

    No Known Activations