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

    Neuronpedia

    INDEX
    Explanations

    questions that start with "how do you" or similar phrasing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndContext
    -0.74
    LookAnd
    -0.73
     Himo
    -0.71
    selves
    -0.67
    }}}}
    -0.67
    судар
    -0.66
     Humb
    -0.63
     Schengen
    -0.63
    těte
    -0.63
     MSF
    -0.61
    POSITIVE LOGITS
     the
    0.73
     malades
    0.69
    Sod
    0.67
    naby
    0.66
    Rüyada
    0.65
    providedIn
    0.64
    contentLoaded
    0.63
     inégal
    0.63
     someone
    0.62
     Condens
    0.61
    Act Density 0.131%

    No Known Activations