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

    Neuronpedia

    INDEX
    Explanations

    instances of negligence or inaction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to insufficient oversight or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    waves
    -0.83
    speech
    -0.78
    flies
    -0.77
    words
    -0.75
    word
    -0.73
    saw
    -0.70
    dar
    -0.68
    quote
    -0.66
    ONSORED
    -0.65
    oak
    -0.64
    POSITIVE LOGITS
    atives
    1.06
    igue
    1.00
    acies
    0.95
    glers
    0.91
    iencies
    0.86
     lax
    0.85
    acy
    0.82
    ativity
    0.80
    eness
    0.78
    ately
    0.77
    Act Density 0.027%

    No Known Activations