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

    Neuronpedia

    INDEX
    Explanations

    references to experimental studies and results in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gue
    -0.20
    hammer
    -0.17
    rase
    -0.16
    alus
    -0.15
    ults
    -0.15
    ufs
    -0.15
    andom
    -0.15
    Ļ¨
    -0.15
     gam
    -0.14
    rende
    -0.14
    POSITIVE LOGITS
    ADOR
    0.16
    abant
    0.15
    brtc
    0.14
    abwe
    0.14
    Ń
    0.14
     Wings
    0.14
    ador
    0.13
    idar
    0.13
     consideration
    0.13
    LIKELY
    0.13
    Act Density 0.014%

    No Known Activations