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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "it's not that" followed by a descriptor

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a contrast or rejection of a notion or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hips
    -0.66
     Haz
    -0.63
    ãĥij
    -0.63
    ãĥ¡
    -0.63
    Ö¼
    -0.61
    ×Ļ×
    -0.61
    ×Ļ
    -0.61
     Hew
    -0.60
    mi
    -0.60
    ×ŀ
    -0.56
    POSITIVE LOGITS
    interstitial
    0.81
    cher
    0.75
     pesky
    0.74
    same
    0.73
    ched
    0.71
    angular
    0.70
    glomer
    0.68
    andestine
    0.67
    emic
    0.67
     fateful
    0.66
    Act Density 0.187%

    No Known Activations