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

    Neuronpedia

    INDEX
    Explanations

    phrases about the relationship between actions and their effects or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vale
    -0.15
    ood
    -0.14
    etter
    -0.13
    ÑĤим
    -0.13
    _cu
    -0.13
    osis
    -0.13
     ÐŁÑĢа
    -0.13
    gewater
    -0.13
    ogan
    -0.13
    .NULL
    -0.13
    POSITIVE LOGITS
     unrelated
    0.17
    qli
    0.14
    inject
    0.14
    adaki
    0.14
    ationship
    0.14
    ungan
    0.14
    idot
    0.13
    ugi
    0.13
    ëł
    0.13
    unately
    0.13
    Act Density 0.045%

    No Known Activations