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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence or security-related positions within a bureaucratic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Atomic
    -0.17
    aload
    -0.15
    obierno
    -0.15
    aises
    -0.15
    bish
    -0.15
    æ±Ĥè´Ń
    -0.15
    arnation
    -0.15
     Ownership
    -0.15
     committee
    -0.14
    ůr
    -0.14
    POSITIVE LOGITS
    iaux
    0.18
     civil
    0.17
     Civil
    0.17
     feeder
    0.16
     hob
    0.15
    .argument
    0.15
     gazet
    0.15
    asher
    0.15
     h
    0.15
    ONUS
    0.14
    Act Density 0.134%

    No Known Activations