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

    Neuronpedia

    INDEX
    Explanations

    words related to global or societal issues and events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to global and societal conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.68
     Fas
    -0.67
    edin
    -0.66
     sqor
    -0.66
    bourg
    -0.65
    achment
    -0.64
    taining
    -0.63
    Dur
    -0.63
     Sell
    -0.62
    Sem
    -0.62
    POSITIVE LOGITS
     reacted
    0.96
     tremb
    0.95
     erupted
    0.90
     loves
    0.88
     revolves
    0.87
     reacts
    0.86
     froze
    0.84
     awoke
    0.84
     intervened
    0.83
     thri
    0.82
    Act Density 0.488%

    No Known Activations