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

    Neuronpedia

    INDEX
    Explanations

    terms related to controversial or impactful topics or debates

    oai_token-act-pair · gpt-3.5-turbo

    recurring references to significant topics or concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rams
    -0.81
    emouth
    -0.78
    ramid
    -0.78
    urses
    -0.77
    ongyang
    -0.76
    ãĥ³ãĤ¸
    -0.75
    ancies
    -0.75
    anova
    -0.75
    ittle
    -0.74
    ramids
    -0.74
    POSITIVE LOGITS
     confronting
    0.81
     facing
    0.78
     flared
    0.78
     HRC
    0.76
     raised
    0.76
     arising
    0.72
     tracker
    0.71
     relating
    0.71
     plag
    0.70
     arises
    0.69
    Act Density 0.042%

    No Known Activations