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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to habits and behavioral patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ende
    -0.15
    duk
    -0.15
    /release
    -0.14
    ode
    -0.14
    isse
    -0.13
    sure
    -0.13
    ductive
    -0.13
    265
    -0.13
    sv
    -0.13
    du
    -0.13
    POSITIVE LOGITS
    oyal
    0.17
    ÃĹ↵↵
    0.17
    inkel
    0.17
     of
    0.17
     ofs
    0.16
    iasi
    0.14
    _kwargs
    0.14
    aç
    0.14
    Sink
    0.14
    atown
    0.14
    Act Density 0.281%

    No Known Activations