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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional probabilities and statistical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĺħâĺħ
    -0.15
    -mouth
    -0.14
    å¤ĩ
    -0.14
    rega
    -0.14
    öm
    -0.14
    ENCIL
    -0.14
    lein
    -0.14
    psc
    -0.13
    ehr
    -0.13
    .delta
    -0.13
    POSITIVE LOGITS
    aly
    0.17
    ally
    0.16
    als
    0.16
    Ļ¨
    0.15
    ALLY
    0.15
    jin
    0.15
    449
    0.15
    ities
    0.15
    -release
    0.14
    backs
    0.14
    Act Density 0.070%

    No Known Activations