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

    Neuronpedia

    INDEX
    Explanations

    keywords related to events or announcements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to events and societal issues involving resources or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.89
    orically
    -0.76
    oulos
    -0.74
    ocate
    -0.73
    ngth
    -0.73
    arnaev
    -0.73
    nown
    -0.70
    ptin
    -0.69
    eger
    -0.68
    GGGGGGGG
    -0.67
    POSITIVE LOGITS
     occasions
    1.41
     basis
    1.05
     occasion
    0.95
     behalf
    0.95
     grounds
    0.90
     eve
    0.85
     shores
    0.85
    ilts
    0.84
     forums
    0.84
     fronts
    0.82
    Act Density 0.343%

    No Known Activations