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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or authoritative actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to enforcement actions or efforts to reduce certain behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sake
    -0.71
    ensical
    -0.69
    æµ
    -0.68
    join
    -0.64
     Upton
    -0.63
    hof
    -0.61
     Norn
    -0.61
     anecdote
    -0.61
     Nobel
    -0.60
     Tribe
    -0.60
    POSITIVE LOGITS
    orously
    0.81
     enforcement
    0.76
     territ
    0.76
    senal
    0.71
     enforced
    0.71
    agra
    0.70
    ERA
    0.69
     administr
    0.68
     against
    0.67
     enforcing
    0.67
    Act Density 0.050%

    No Known Activations