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

    Neuronpedia

    INDEX
    Explanations

    words related to disasters and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to crises, disasters, and significant societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynthesis
    -0.78
    ij
    -0.76
    gemony
    -0.76
    etheless
    -0.74
    hran
    -0.73
    thora
    -0.69
    Semitism
    -0.67
    comings
    -0.65
    ularity
    -0.65
    stanbul
    -0.64
    POSITIVE LOGITS
     prevention
    1.73
     Prevention
    1.44
     mitigation
    1.43
     detection
    1.16
     avoidance
    1.08
     victims
    1.07
     survivor
    1.06
    proof
    1.03
     Detection
    1.02
     survivors
    1.02
    Act Density 0.289%

    No Known Activations