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

    Neuronpedia

    INDEX
    Explanations

    references to significant numerical achievements or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çª
    -0.18
    ÑģÑĤи
    -0.15
    OVE
    -0.15
    çŃĭ
    -0.15
    aval
    -0.14
    039
    -0.14
    finder
    -0.13
    ayah
    -0.13
    inz
    -0.13
     mand
    -0.13
    POSITIVE LOGITS
    chyb
    0.15
     å¾Ĵ
    0.15
    mad
    0.14
    iscal
    0.14
     ALOG
    0.14
     Dagger
    0.14
    WISE
    0.14
    isson
    0.13
    Bezier
    0.13
    ichtig
    0.13
    Act Density 0.056%

    No Known Activations