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

    Neuronpedia

    INDEX
    Explanations

    terms related to mortality and negative impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Escort
    -0.15
     elems
    -0.14
    898
    -0.14
    akin
    -0.14
     escorts
    -0.14
    egov
    -0.13
    Escort
    -0.13
    841
    -0.13
     Epic
    -0.13
    Âį
    -0.13
    POSITIVE LOGITS
     em
    0.88
    -em
    0.84
     Em
    0.80
    em
    0.77
    Em
    0.76
    _em
    0.75
    .em
    0.73
     EM
    0.72
    EM
    0.66
    'em
    0.59
    Act Density 0.209%

    No Known Activations