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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating failure or disappointing outcomes

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of something not being done or absent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĥ
    -0.68
    æĥ
    -0.67
    rift
    -0.65
    Pierre
    -0.65
    itor
    -0.63
    CRIP
    -0.63
    ++++
    -0.62
    Rap
    -0.61
     weap
    -0.60
     Spectrum
    -0.60
    POSITIVE LOGITS
    epad
    1.11
    icably
    1.08
     yet
    1.08
    icable
    1.07
     been
    1.01
    yet
    0.96
     necessarily
    0.96
    hin
    0.90
     gotten
    0.85
     fared
    0.83
    Act Density 0.055%

    No Known Activations