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

    Neuronpedia

    INDEX
    Explanations

    words that indicate strong affirmations or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierarchy
    -0.17
    NV
    -0.17
    -vars
    -0.16
    osto
    -0.15
    contre
    -0.15
    ÑĢаÑĩ
    -0.14
    edor
    -0.14
     Conc
    -0.14
    .BUTTON
    -0.14
    ront
    -0.14
    POSITIVE LOGITS
    indh
    0.16
    ãĥ«ãĥĪ
    0.15
    /MIT
    0.14
    lius
    0.14
    ruž
    0.14
    .routing
    0.14
    unan
    0.14
     Chance
    0.14
    (CG
    0.14
    azzi
    0.14
    Act Density 0.000%

    No Known Activations