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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capabilities and functional attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uch
    -0.19
    egie
    -0.18
    ãĥŃãĥ¼
    -0.17
    ucch
    -0.17
     koc
    -0.16
    bjerg
    -0.16
    uche
    -0.15
    utzer
    -0.15
    ollo
    -0.15
    insky
    -0.15
    POSITIVE LOGITS
    569
    0.15
    phans
    0.14
     Surv
    0.14
     cob
    0.13
    ÅĤad
    0.13
    iao
    0.13
    è¾¼
    0.13
    erto
    0.13
    çĸ²
    0.12
     patch
    0.12
    Act Density 0.045%

    No Known Activations