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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or results related to theorems and equations in academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thumb
    -0.15
    inate
    -0.14
    udo
    -0.14
    ertz
    -0.14
    ÅĻet
    -0.14
     bolt
    -0.14
     Proceed
    -0.13
    unta
    -0.13
     ê²
    -0.13
    pur
    -0.13
    POSITIVE LOGITS
    á»ĥm
    0.15
    лоÑĩ
    0.15
    mlink
    0.14
    rovers
    0.14
    Prefs
    0.14
    announce
    0.13
     Thou
    0.13
    oren
    0.13
    anko
    0.13
    ãĤµãĥ¼
    0.13
    Act Density 0.062%

    No Known Activations