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

    Neuronpedia

    INDEX
    Explanations

    references to hierarchical structures or attributes related to projects or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃna
    -0.18
    ruba
    -0.17
     witch
    -0.15
    _OT
    -0.15
     Truy
    -0.15
    filme
    -0.15
     tack
    -0.14
    ÃŃny
    -0.14
     lunches
    -0.14
    ince
    -0.14
    POSITIVE LOGITS
    Ñģп
    0.16
    ucch
    0.15
    unga
    0.15
     Mayer
    0.15
     Dub
    0.14
    Fld
    0.14
    /../
    0.13
     Fucked
    0.13
    Posting
    0.13
    Dub
    0.13
    Act Density 0.582%

    No Known Activations