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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "past."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SEC
    -0.16
    athers
    -0.15
    fang
    -0.15
    -Men
    -0.14
    igan
    -0.14
    inth
    -0.14
    åIJĪ
    -0.14
    ersen
    -0.13
    orsi
    -0.13
    adius
    -0.13
    POSITIVE LOGITS
    usch
    0.19
    illard
    0.16
    sans
    0.15
    лиÑĪком
    0.15
    Sharper
    0.14
    ouro
    0.14
    istry
    0.14
    esium
    0.14
    ooth
    0.14
     Freed
    0.13
    Act Density 0.021%

    No Known Activations