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

    Neuronpedia

    INDEX
    Explanations

    words related to scandals

    oai_token-act-pair · gpt-3.5-turbo

    references to scandals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    requisite
    -0.69
    cki
    -0.67
    hetics
    -0.66
    lasses
    -0.65
    ignty
    -0.63
    ports
    -0.62
     Swords
    -0.60
     mathemat
    -0.60
    icrobial
    -0.60
    ramer
    -0.59
    POSITIVE LOGITS
     involving
    1.01
     scandals
    0.98
     revolving
    0.98
     scandal
    0.94
    ous
    0.92
    ously
    0.90
    icity
    0.90
     plag
    0.88
     erupted
    0.82
     engulf
    0.78
    Act Density 0.041%

    No Known Activations