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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific types of entities, especially objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of various subjects or themes across multiple contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rehensive
    -0.75
    igan
    -0.67
    obook
    -0.65
    apult
    -0.64
    è¦ļéĨĴ
    -0.64
    zon
    -0.63
    soType
    -0.62
    Alert
    -0.61
    ibe
    -0.61
    escription
    -0.61
    POSITIVE LOGITS
     where
    0.88
     there
    0.88
     however
    0.82
    there
    0.81
    where
    0.79
     whenever
    0.77
     moreover
    0.75
     meanwhile
    0.75
     sometimes
    0.74
     unless
    0.70
    Act Density 0.235%

    No Known Activations