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

    Neuronpedia

    INDEX
    Explanations

    words related to strong emotions or exaggerated adjectives

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors related to emotions and character traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matically
    -0.83
    ajor
    -0.82
    resent
    -0.81
    yrim
    -0.77
     largeDownload
    -0.77
    orously
    -0.77
    lessly
    -0.75
    illary
    -0.72
    owing
    -0.72
    lished
    -0.71
    POSITIVE LOGITS
     Ones
    1.17
    ness
    1.10
     Skies
    1.02
     Bastard
    0.96
     Isles
    0.96
     Mind
    0.95
     Guys
    0.95
     Universe
    0.95
     Monkey
    0.95
     Realms
    0.94
    Act Density 0.198%

    No Known Activations