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

    Neuronpedia

    INDEX
    Explanations

    terms related to naming conventions and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    compat
    -0.19
    isti
    -0.17
    amedi
    -0.15
     Alexand
    -0.15
    par
    -0.15
    mary
    -0.15
     Pratt
    -0.15
    eldom
    -0.14
    quia
    -0.14
    pt
    -0.14
    POSITIVE LOGITS
    aho
    0.16
    ovÃŃ
    0.15
    Ŀi
    0.14
    @dynamic
    0.14
    διο
    0.14
    SWEP
    0.14
    .nanoTime
    0.14
     launder
    0.13
    AKE
    0.13
    кÑĥл
    0.13
    Act Density 0.005%

    No Known Activations