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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs related to criticisms or negative opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    perture
    -0.67
    BILITIES
    -0.66
    phia
    -0.65
    ICAN
    -0.65
    endez
    -0.65
    IELD
    -0.64
    ãĥ¤
    -0.64
    perature
    -0.63
     NASCAR
    -0.62
    flies
    -0.62
    POSITIVE LOGITS
    ratulations
    1.25
    regate
    1.16
    lasses
    1.08
    regor
    1.01
    lass
    0.97
    jiang
    0.95
    atana
    0.95
    uay
    0.90
    oing
    0.83
    ueless
    0.82
    Act Density 0.081%

    No Known Activations