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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating formal recognition or commendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )||(
    -0.16
    onymous
    -0.16
    lse
    -0.15
    iyon
    -0.14
    nun
    -0.14
    ilib
    -0.14
    è½
    -0.14
     poh
    -0.14
     spared
    -0.14
    andi
    -0.14
    POSITIVE LOGITS
    ypad
    0.15
     SPDX
    0.15
    uddle
    0.15
    phabet
    0.14
    XMLLoader
    0.14
    antas
    0.14
    BuilderInterface
    0.14
    okud
    0.14
     {{{
    0.14
    issement
    0.13
    Act Density 0.044%

    No Known Activations