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

    Neuronpedia

    INDEX
    Explanations

    Titles and authors in academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /trunk
    -0.16
    elian
    -0.16
     Crescent
    -0.16
    krom
    -0.15
    contres
    -0.15
     Nash
    -0.15
    iversit
    -0.15
    ÙIJÙĬ
    -0.14
    icari
    -0.14
    uario
    -0.14
    POSITIVE LOGITS
     statist
    0.19
     Hast
    0.19
     Dia
    0.17
    abr
    0.17
     ESL
    0.17
    imas
    0.16
     Tib
    0.16
     Gentle
    0.15
     Wake
    0.15
     ple
    0.15
    Act Density 0.032%

    No Known Activations