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

    Neuronpedia

    INDEX
    Explanations

    references to awards or notable achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plex
    -0.16
    vala
    -0.16
    iam
    -0.16
    ple
    -0.15
    cor
    -0.15
    ea
    -0.15
    สà¸Ķ
    -0.14
    blo
    -0.14
    ling
    -0.14
     contempt
    -0.14
    POSITIVE LOGITS
    undry
    0.18
    ereo
    0.17
    اتÙĩ
    0.17
    enor
    0.17
    enos
    0.17
    quer
    0.16
    erts
    0.16
    iston
    0.15
    ughter
    0.15
    clado
    0.15
    Act Density 0.074%

    No Known Activations