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

    Neuronpedia

    INDEX
    Explanations

    instances of negative statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "not"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CRIP
    -0.67
    æĥ
    -0.67
    ++++
    -0.65
    éĥ
    -0.64
    GEN
    -0.61
    Pierre
    -0.60
    rift
    -0.60
    vice
    -0.60
    Pr
    -0.60
     Spectrum
    -0.59
    POSITIVE LOGITS
     yet
    1.09
     been
    1.08
    epad
    1.03
    icably
    1.01
    icable
    0.99
    yet
    0.96
     necessarily
    0.93
    hin
    0.93
     gotten
    0.91
    been
    0.89
    Act Density 0.051%

    No Known Activations