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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global issues

    oai_token-act-pair · gpt-3.5-turbo

    mentions of global topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.98
    maid
    -0.91
    _-
    -0.85
    HOU
    -0.83
    WARE
    -0.80
    rentice
    -0.78
    eva
    -0.75
    ippi
    -0.75
     [&
    -0.75
    sbm
    -0.75
    POSITIVE LOGITS
     warming
    1.16
    isation
    1.03
    ized
    0.95
    ization
    0.91
    ised
    0.89
     positioning
    0.87
     illumination
    0.85
     citizenship
    0.85
    izable
    0.83
     economy
    0.82
    Act Density 0.031%

    No Known Activations