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

    Neuronpedia

    INDEX
    Explanations

    words related to debates and discussions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to discussions and debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ®å
    -0.75
    é¾įå
    -0.64
    parse
    -0.60
    oku
    -0.60
    elin
    -0.58
    iola
    -0.57
    oho
    -0.57
     boss
    -0.57
     accountant
    -0.56
    merga
    -0.56
    POSITIVE LOGITS
     regarding
    1.11
     concerning
    1.10
     surrounding
    1.09
     about
    1.07
     raging
    1.07
     raged
    1.03
     around
    0.96
     revolving
    0.95
     forums
    0.92
     swirling
    0.91
    Act Density 0.182%

    No Known Activations