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

    Neuronpedia

    INDEX
    Explanations

    terms related to interpretation and dissemination in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogg
    -0.22
    odd
    -0.21
    enn
    -0.20
    ify
    -0.20
    ock
    -0.20
    ell
    -0.20
    egg
    -0.20
    elf
    -0.19
    ett
    -0.19
    ells
    -0.19
    POSITIVE LOGITS
    ctions
    0.34
    ction
    0.31
    ctal
    0.31
    brate
    0.28
    ctor
    0.28
    ption
    0.28
    ducible
    0.28
    brates
    0.28
    mination
    0.27
    ptive
    0.27
    Act Density 0.063%

    No Known Activations