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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and terms indicating contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GGLE
    -0.17
    acs
    -0.16
    pillar
    -0.15
     Wesley
    -0.15
    Reviewed
    -0.14
    WI
    -0.14
    æ¹
    -0.14
     Shapiro
    -0.14
     Unicode
    -0.14
     stakes
    -0.14
    POSITIVE LOGITS
     Whereas
    0.28
     whereas
    0.27
     unlike
    0.25
     compared
    0.19
    Unlike
    0.19
     Unlike
    0.19
     others
    0.19
    others
    0.18
     mine
    0.16
    407
    0.15
    Act Density 0.279%

    No Known Activations