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

    Neuronpedia

    INDEX
    Explanations

    questions that begin with "how do you" or "what do you"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.76
    EndContext
    -0.72
    selves
    -0.63
    herself
    -0.60
     أنه
    -0.59
     always
    -0.59
    судар
    -0.59
     Humb
    -0.58
    enchymal
    -0.58
     Chbosky
    -0.58
    POSITIVE LOGITS
    providedIn
    0.74
     malades
    0.66
     Thad
    0.64
     inégal
    0.63
    Sod
    0.63
     Marston
    0.63
     ihop
    0.62
     Nadel
    0.62
     gordo
    0.62
    ESSO
    0.61
    Act Density 0.098%

    No Known Activations