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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uffers
    -0.16
    ardon
    -0.15
    agar
    -0.15
     Canter
    -0.15
    774
    -0.15
    istr
    -0.14
    marker
    -0.14
    endo
    -0.14
    TAG
    -0.13
    ape
    -0.13
    POSITIVE LOGITS
     Colleg
    0.16
    .prof
    0.15
    ORA
    0.14
    contri
    0.14
    ynos
    0.14
    ï¸
    0.13
    ityEngine
    0.13
    icari
    0.13
    ImageContext
    0.13
    imi
    0.13
    Act Density 0.051%

    No Known Activations