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

    Neuronpedia

    INDEX
    Explanations

    terms related to all-inclusive features or offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bjerg
    -0.16
    shield
    -0.15
    owo
    -0.15
    ceased
    -0.15
    islav
    -0.14
    alfa
    -0.14
    ekt
    -0.14
    furt
    -0.14
    yonel
    -0.14
    illions
    -0.13
    POSITIVE LOGITS
    igator
    0.17
    endale
    0.17
    rou
    0.15
    ness
    0.15
    mut
    0.14
    igators
    0.14
    IRCLE
    0.14
    wo
    0.14
    otre
    0.13
    bie
    0.13
    Act Density 0.045%

    No Known Activations