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

    Neuronpedia

    INDEX
    Explanations

    concepts related to information theory and randomness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ION
    -0.15
    ODO
    -0.15
    erator
    -0.14
    unca
    -0.13
    ug
    -0.13
    otto
    -0.13
    izzo
    -0.13
    elf
    -0.13
    Ion
    -0.13
    lops
    -0.13
    POSITIVE LOGITS
    arkin
    0.16
    اتر
    0.14
     resignation
    0.14
     Humph
    0.14
    arrow
    0.14
    bst
    0.14
    æk
    0.13
    ække
    0.13
    azor
    0.13
    ourke
    0.13
    Act Density 0.005%

    No Known Activations