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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to expressions of strong opinions or emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong opinion or vocal criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akeru
    -1.03
    uden
    -1.01
    atch
    -0.84
    ramid
    -0.84
    pty
    -0.83
    ovember
    -0.79
    ueller
    -0.76
    issors
    -0.72
    arcity
    -0.69
    annis
    -0.68
    POSITIVE LOGITS
     outspoken
    1.00
    ness
    0.95
     exponent
    0.84
     personalities
    0.83
     critic
    0.81
    odox
    0.81
     campaigner
    0.79
    ly
    0.78
     activist
    0.76
     leader
    0.74
    Act Density 0.013%

    No Known Activations