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

    Neuronpedia

    INDEX
    Explanations

    references to the top and bottom positions or edges in a spatial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hest
    -0.19
    zn
    -0.18
    mdir
    -0.17
     AuthenticationService
    -0.15
     intros
    -0.15
    uming
    -0.14
    ạm
    -0.14
    æ®
    -0.14
     odpad
    -0.14
    éĥİ
    -0.13
    POSITIVE LOGITS
    most
    0.20
    fu
    0.17
    cps
    0.17
    loys
    0.15
     most
    0.14
    doch
    0.14
    chk
    0.14
     quote
    0.13
    mods
    0.13
    alker
    0.13
    Act Density 0.047%

    No Known Activations