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

    Neuronpedia

    INDEX
    Explanations

    direct speech and commands within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noreferrer
    -0.15
    oles
    -0.15
    rophe
    -0.15
    aldi
    -0.15
    esome
    -0.14
    å³°
    -0.14
    _HELPER
    -0.14
    iÄįky
    -0.14
    liable
    -0.14
    COPE
    -0.14
    POSITIVE LOGITS
     stay
    0.15
    thal
    0.15
     मत
    0.15
    tha
    0.14
     thou
    0.14
     Spl
    0.14
    stay
    0.13
    θι
    0.13
    pace
    0.13
    ered
    0.13
    Act Density 0.276%

    No Known Activations