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

    Neuronpedia

    INDEX
    Explanations

    references to theoretical frameworks and models in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afa
    -0.17
    elmet
    -0.16
    illez
    -0.15
    unger
    -0.14
    fal
    -0.14
     gele
    -0.14
     flaw
    -0.13
     toto
    -0.13
    erez
    -0.13
    导
    -0.13
    POSITIVE LOGITS
    ysis
    0.18
    igue
    0.16
     implications
    0.15
    óst
    0.15
    icus
    0.14
    case
    0.14
     how
    0.13
    ynos
    0.13
    ObjectContext
    0.13
    cción
    0.13
    Act Density 0.048%

    No Known Activations