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

    Neuronpedia

    INDEX
    Explanations

    phrases related to thoughts and opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Allister
    -0.64
    Leod
    -0.58
    Millan
    -0.57
    ಘ
    -0.56
    arrol
    -0.53
    Cormack
    -0.53
     Quem
    -0.50
    ėjimas
    -0.49
    Oof
    -0.48
     Permite
    -0.48
    POSITIVE LOGITS
     THOUGHT
    0.98
     THINK
    0.97
     scrat
    0.96
     affez
    0.87
     motorola
    0.86
     Think
    0.86
     shenan
    0.85
     thut
    0.85
     maneu
    0.85
     pollut
    0.84
    Act Density 0.145%

    No Known Activations