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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives indicating strong emotions or opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Awakening
    -0.71
    ilan
    -0.69
     Participants
    -0.65
    iful
    -0.63
    adium
    -0.62
    coming
    -0.62
     Landing
    -0.62
     simultaneous
    -0.61
     Flore
    -0.60
     Altern
    -0.60
    POSITIVE LOGITS
     ought
    1.08
     appreciate
    0.97
     shouldn
    0.88
     deserved
    0.86
     cared
    0.85
     deserve
    0.84
     liked
    0.82
     enjoyed
    0.82
     owe
    0.81
     behaved
    0.80
    Act Density 0.055%

    No Known Activations