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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    902
    -0.15
    orsi
    -0.14
    ort
    -0.14
    ROUGH
    -0.14
    .writeln
    -0.14
    orton
    -0.13
    nl
    -0.13
    antage
    -0.13
     Yates
    -0.13
    agas
    -0.13
    POSITIVE LOGITS
    elop
    0.21
    avou
    0.15
    á»±c
    0.14
     Dumpster
    0.14
     derec
    0.14
    adeon
    0.13
    emonic
    0.13
    iyim
    0.13
    uta
    0.13
    aven
    0.13
    Act Density 0.208%

    No Known Activations