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

    Neuronpedia

    INDEX
    Explanations

    terms associated with statistical data and demographic breakdowns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovsky
    -0.16
    æ¾
    -0.15
    orent
    -0.15
    alsy
    -0.15
    nodoc
    -0.15
    cker
    -0.14
    ãĥĸãĥ«
    -0.14
    RGB
    -0.14
    аниÑĨ
    -0.14
    опиÑģ
    -0.14
    POSITIVE LOGITS
     leather
    0.23
     lic
    0.23
     Leather
    0.21
     tobacco
    0.20
     vanilla
    0.19
     hints
    0.19
     earth
    0.19
     oak
    0.19
     toast
    0.19
     fig
    0.19
    Act Density 0.015%

    No Known Activations