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

    Neuronpedia

    INDEX
    Explanations

    phrases related to enjoyment and positivity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ئ
    -0.16
    odiac
    -0.15
    ¸
    -0.15
    hti
    -0.15
    ternet
    -0.15
    amos
    -0.14
    μη
    -0.14
    arkin
    -0.14
    ht
    -0.14
    amo
    -0.14
    POSITIVE LOGITS
    !
    0.21
    !,
    0.20
    !.
    0.15
    !--
    0.15
    !/
    0.14
    rud
    0.14
    £
    0.14
    بÛĮر
    0.13
    ulta
    0.13
    BILL
    0.13
    Act Density 0.037%

    No Known Activations