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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating belief or speculation

    oai_token-act-pair · gpt-3.5-turbo

    assertions of belief or speculation about people or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mentioned
    -0.75
    ample
    -0.70
    cloth
    -0.68
    Interstitial
    -0.68
    ãģį
    -0.68
    ECK
    -0.67
    Newsletter
    -0.67
    talk
    -0.64
    Against
    -0.62
    jab
    -0.60
    POSITIVE LOGITS
    lessly
    0.87
    fully
    0.78
     destined
    0.74
     responsible
    0.72
     haunted
    0.70
    ril
    0.70
     guilty
    0.67
     abducted
    0.65
     intact
    0.65
     unrelated
    0.65
    Act Density 0.077%

    No Known Activations