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

    Neuronpedia

    INDEX
    Explanations

    concepts related to theoretical ideas and possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    canonical
    -0.18
     Canter
    -0.17
    apol
    -0.17
     canon
    -0.17
     Cant
    -0.15
     canonical
    -0.15
     Canary
    -0.15
    άνÏī
    -0.15
    cac
    -0.15
    canvas
    -0.15
    POSITIVE LOGITS
     could
    1.05
    could
    0.93
     Could
    0.90
    Could
    0.84
     kunne
    0.54
     CO
    0.52
     могли
    0.52
     konnte
    0.50
     могла
    0.48
    ULD
    0.46
    Act Density 0.447%

    No Known Activations