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

    Neuronpedia

    INDEX
    Explanations

    phrases related to probability and risk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amar
    -0.16
    entions
    -0.15
    ington
    -0.15
    oras
    -0.15
    麦
    -0.15
     Bye
    -0.15
    ippo
    -0.14
    eb
    -0.14
    agraph
    -0.13
    ummy
    -0.13
    POSITIVE LOGITS
     chance
    0.23
     Chance
    0.17
    bilt
    0.17
     odds
    0.16
     chances
    0.16
    ivet
    0.16
    lea
    0.16
    assi
    0.15
    _chance
    0.15
     Supreme
    0.14
    Act Density 0.140%

    No Known Activations