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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     c
    -0.16
    -0.16
    mock
    -0.15
    but
    -0.15
    [
    -0.14
    249
    -0.14
    mor
    -0.14
    llen
    -0.14
    ,
    -0.14
    Alias
    -0.14
    POSITIVE LOGITS
    ema
    0.16
    ode
    0.16
     Til
    0.15
    -uri
    0.15
    ErrorException
    0.15
    ultip
    0.14
     Sesso
    0.14
    reater
    0.14
    /preferences
    0.14
     nonatomic
    0.14
    Act Density 0.064%

    No Known Activations