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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating abundance or availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "';
    -0.16
    cycle
    -0.15
    asthan
    -0.14
    mq
    -0.14
    pee
    -0.14
    ège
    -0.13
    IVATE
    -0.13
    phans
    -0.13
     gì
    -0.13
    536
    -0.13
    POSITIVE LOGITS
    yyy
    0.18
    yyyy
    0.17
     enough
    0.15
    sı
    0.15
    uh
    0.15
    irth
    0.14
    enne
    0.14
    erc
    0.14
    eva
    0.14
    ois
    0.14
    Act Density 0.021%

    No Known Activations