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

    Neuronpedia

    INDEX
    Explanations

    concepts related to challenges and principles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.14
    affen
    -0.14
    afi
    -0.14
     AFF
    -0.14
    athom
    -0.14
     aff
    -0.13
    еÑĤи
    -0.13
    cia
    -0.13
    ufen
    -0.13
    cke
    -0.13
    POSITIVE LOGITS
    arsers
    0.17
    -Ta
    0.16
    ektor
    0.16
    aroo
    0.15
    ว
    0.15
    еÑĢап
    0.14
    AndGet
    0.14
    ylko
    0.14
    oulouse
    0.14
    .divide
    0.14
    Act Density 0.183%

    No Known Activations