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

    Neuronpedia

    INDEX
    Explanations

    code-related elements in programming and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     otherwise
    -0.15
    овеÑĢ
    -0.15
    rames
    -0.15
    acct
    -0.15
    éĬ
    -0.15
    pee
    -0.14
    endent
    -0.13
    ero
    -0.13
    aar
    -0.13
    act
    -0.13
    POSITIVE LOGITS
    ubat
    0.16
    ाण
    0.15
    icz
    0.14
    .reflect
    0.14
    ideo
    0.14
    ertiary
    0.14
    adaki
    0.13
    ilities
    0.13
     super
    0.13
     beh
    0.13
    Act Density 0.045%

    No Known Activations