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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    برÛĮ
    -0.16
    wan
    -0.15
     RegexOptions
    -0.15
    loat
    -0.15
    ĵåIJį
    -0.13
    ffa
    -0.13
     lasted
    -0.13
    æķ¦
    -0.13
    rone
    -0.13
    edin
    -0.13
    POSITIVE LOGITS
     boiled
    0.47
     boil
    0.47
     boils
    0.42
     boiling
    0.40
    bo
    0.38
     Bo
    0.38
     rev
    0.35
    -bo
    0.32
    .bo
    0.31
    _bo
    0.31
    Act Density 0.132%

    No Known Activations