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

    Neuronpedia

    INDEX
    Explanations

    adjectives expressing extreme emotions or exaggerations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pai
    -0.75
    anners
    -0.73
    ringe
    -0.72
    deen
    -0.71
    pring
    -0.70
    ©¶æ
    -0.68
    okes
    -0.68
    enhagen
    -0.67
    nery
    -0.67
    olith
    -0.65
    POSITIVE LOGITS
     amounts
    1.10
     proportions
    1.08
     amount
    0.99
     unbeliev
    0.90
     firepower
    0.83
     pandemonium
    0.81
     quantities
    0.80
    !!!!!
    0.80
     feats
    0.80
    ulously
    0.79
    Act Density 2.850%

    No Known Activations