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

    Neuronpedia

    INDEX
    Explanations

    academic references to research and scholarship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rao
    -0.15
    elm
    -0.15
    ensch
    -0.15
    è¾¼
    -0.15
    oken
    -0.15
    urrent
    -0.14
     lanc
    -0.14
     Mev
    -0.14
    iger
    -0.14
    academic
    -0.14
    POSITIVE LOGITS
     обоÑĢ
    0.16
    /topics
    0.15
    obook
    0.14
    екаÑĢ
    0.14
    _mk
    0.14
    .pkg
    0.14
    anke
    0.14
    Ĥæķ°
    0.14
    647
    0.13
    _Syntax
    0.13
    Act Density 0.166%

    No Known Activations