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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and observations about ongoing events

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding social or economic crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Contributions
    -0.66
    ocular
    -0.65
     Feather
    -0.63
     Romance
    -0.63
     sincerity
    -0.63
     validity
    -0.62
     promotional
    -0.61
     Packs
    -0.61
     Revel
    -0.60
    ulence
    -0.59
    POSITIVE LOGITS
     witnessing
    1.29
     incarcer
    1.03
     witnessed
    0.92
     witness
    0.91
     seeing
    0.89
     electing
    0.89
    hower
    0.83
     overdue
    0.81
     faced
    0.80
    akening
    0.80
    Act Density 0.224%

    No Known Activations