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

    Neuronpedia

    INDEX
    Explanations

    mentions of trademarks or company names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of trademarks or brand names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gie
    -0.67
    hold
    -0.64
    gets
    -0.61
     wi
    -0.60
     thumbs
    -0.59
     tipped
    -0.58
    rend
    -0.58
     Beg
    -0.57
    aways
    -0.57
     Hath
    -0.56
    POSITIVE LOGITS
    useum
    1.17
    ISSION
    1.16
    ORPG
    1.14
    ONEY
    1.09
    essage
    1.03
    obile
    1.03
    EGA
    1.03
    ilitary
    1.01
    ODE
    1.01
    ETHOD
    1.01
    Act Density 0.097%

    No Known Activations