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

    Neuronpedia

    INDEX
    Explanations

    references to the size and type of items described as "medium."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gregory
    -0.17
    stad
    -0.17
    lsru
    -0.15
    aload
    -0.14
    ør
    -0.14
    /umd
    -0.13
    abilit
    -0.13
    Äįit
    -0.13
    anz
    -0.13
    ucer
    -0.13
    POSITIVE LOGITS
    -sized
    0.24
     sized
    0.19
    alam
    0.17
    wares
    0.17
     Sized
    0.16
    veis
    0.16
    -length
    0.15
    -size
    0.15
    ç´¹
    0.15
    /high
    0.14
    Act Density 0.023%

    No Known Activations