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

    Neuronpedia

    INDEX
    Explanations

    instances of confirmation or validation in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arg
    -0.15
    ANA
    -0.15
    ana
    -0.15
    Ø©
    -0.15
    ARCH
    -0.15
    ighth
    -0.15
    allas
    -0.15
    lay
    -0.14
    aque
    -0.14
    OrDefault
    -0.14
    POSITIVE LOGITS
    zik
    0.17
    atively
    0.16
    ably
    0.15
    suppress
    0.15
    oo
    0.14
    uset
    0.14
    ewood
    0.14
    ussen
    0.14
    hid
    0.14
    .readString
    0.14
    Act Density 0.017%

    No Known Activations