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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific person

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĵĺ
    -0.71
    ãĤ´ãĥ³
    -0.68
    grave
    -0.67
     Mechdragon
    -0.62
     Articles
    -0.60
     CLR
    -0.60
    ãĤ¯
    -0.60
    ãĥ¤
    -0.59
    etheless
    -0.58
     Alas
    -0.58
    POSITIVE LOGITS
    zbollah
    1.21
    'll
    1.20
     hates
    1.18
     loves
    1.15
     ain
    1.09
     knows
    1.09
     doesn
    1.09
     thinks
    1.04
    'd
    1.04
     hasn
    1.03
    Act Density 0.210%

    No Known Activations