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

    Neuronpedia

    INDEX
    Explanations

    references to support and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     help
    -0.19
    _help
    -0.18
    asca
    -0.18
     Help
    -0.17
    Help
    -0.17
    HING
    -0.17
    _HELP
    -0.16
    ield
    -0.16
    velte
    -0.16
    chet
    -0.16
    POSITIVE LOGITS
    fully
    0.30
     Äijỡ
    0.29
    desk
    0.28
    lessness
    0.28
    lessly
    0.26
    full
    0.23
     desk
    0.20
    å¿Ļ
    0.19
    /support
    0.19
    ings
    0.19
    Act Density 0.063%

    No Known Activations