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

    Neuronpedia

    INDEX
    Explanations

    references to project statuses and their updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Evaluator
    -0.15
    eso
    -0.15
    æĵ¦
    -0.15
    extras
    -0.14
    expired
    -0.14
    ehr
    -0.13
    ÙĪÙĨÙĬØ©
    -0.13
    ubo
    -0.13
    uned
    -0.13
    _INST
    -0.13
    POSITIVE LOGITS
    ì²ĺ
    0.17
    Å¡ek
    0.15
     state
    0.15
    tep
    0.14
    uts
    0.14
    çĬ¶æĢģ
    0.14
     Needle
    0.14
    è¸ı
    0.14
    riel
    0.13
     Numeric
    0.13
    Act Density 0.060%

    No Known Activations