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

    Neuronpedia

    INDEX
    Explanations

    terms related to negative events or tragedies

    oai_token-act-pair · gpt-3.5-turbo

    words related to tragic events and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.73
    compatible
    -0.70
    requires
    -0.70
    ITH
    -0.69
    spoken
    -0.67
    Types
    -0.66
    IBLE
    -0.65
    english
    -0.65
    FIELD
    -0.64
     specialize
    -0.64
    POSITIVE LOGITS
     debacle
    1.27
     fiasco
    1.21
     revelations
    1.16
     scandals
    1.07
     announcement
    1.06
     recent
    1.05
     controversies
    1.00
     scandal
    0.97
     controversy
    0.93
     Snowden
    0.93
    Act Density 0.947%

    No Known Activations