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

    Neuronpedia

    INDEX
    Explanations

    phrases denoting various issues or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quotes
    -0.15
    ibase
    -0.14
    або
    -0.14
    .INSTANCE
    -0.14
    align
    -0.13
    marvin
    -0.13
    ullet
    -0.13
    .appspot
    -0.13
    ariant
    -0.13
    alle
    -0.13
    POSITIVE LOGITS
    urse
    0.15
     thang
    0.14
    958
    0.14
     tol
    0.14
    ekil
    0.14
    APE
    0.13
     thing
    0.13
    xec
    0.13
    Thing
    0.13
    yth
    0.13
    Act Density 0.053%

    No Known Activations