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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussions or debates on various topics

    oai_token-act-pair · gpt-3.5-turbo

    discussions and debates regarding various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merga
    -0.62
    IER
    -0.60
    AMI
    -0.60
    oku
    -0.60
    parse
    -0.60
    ãģ®å
    -0.58
    iola
    -0.58
     Cele
    -0.57
     robber
    -0.57
    ingers
    -0.55
    POSITIVE LOGITS
     raging
    1.15
     about
    1.03
     raged
    1.03
     surrounding
    1.01
     concerning
    0.98
     regarding
    0.97
     forums
    0.93
     revolving
    0.92
     swirling
    0.89
     forum
    0.89
    Act Density 0.136%

    No Known Activations