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

    Neuronpedia

    INDEX
    Explanations

    phrases related to requirements, permissions, or limitations

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing conditions or necessities for events to occur

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onom
    -0.73
    ãĥĺ
    -0.70
    geist
    -0.70
    raq
    -0.69
    erent
    -0.69
    week
    -0.68
    ãģ®æ
    -0.67
    rolled
    -0.66
    ãģ®éŃĶ
    -0.66
    iers
    -0.65
    POSITIVE LOGITS
     risking
    1.17
     sacrificing
    0.98
     encountering
    0.97
     mentioning
    0.93
     knowing
    0.93
     consulting
    0.91
     recourse
    0.91
     acknowledging
    0.88
     compromising
    0.88
     addressing
    0.85
    Act Density 0.063%

    No Known Activations