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

    Neuronpedia

    INDEX
    Explanations

    words related to psychological concepts and education, such as detachment, repression, reason, law, government, speech, truth, propositions, argument, marketplace, ideas, learning process, reinforcement theory, behavior analysis, and effect

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kham
    -0.65
    psons
    -0.64
    Ire
    -0.63
    aptop
    -0.62
     TEAM
    -0.61
    udeb
    -0.60
     GMT
    -0.59
    ersen
    -0.57
    aughed
    -0.57
    arnaev
    -0.57
    POSITIVE LOGITS
    lessness
    1.06
     versus
    0.92
    fulness
    0.85
    liness
    0.84
    ism
    0.82
    ativity
    0.82
    ivism
    0.81
    atism
    0.81
     vs
    0.79
    cellence
    0.77
    Act Density 0.408%

    No Known Activations