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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to objectives and planned actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argas
    -0.18
    ollo
    -0.18
     Fade
    -0.16
    arga
    -0.15
    BS
    -0.14
    apons
    -0.14
    assen
    -0.14
    ero
    -0.14
     Hundred
    -0.14
    meer
    -0.14
    POSITIVE LOGITS
    ctype
    0.17
    HeaderCode
    0.15
    atis
    0.15
    ivet
    0.14
    resco
    0.14
    (s
    0.14
    /environment
    0.14
    iveau
    0.14
    RuntimeObject
    0.14
     Undert
    0.14
    Act Density 0.125%

    No Known Activations