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

    Neuronpedia

    INDEX
    Explanations

    terms related to electricity and energy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.20
    ein
    -0.20
    ร
    -0.20
    hook
    -0.19
    ing
    -0.19
    ings
    -0.19
    eat
    -0.18
    haf
    -0.18
    scape
    -0.18
    tings
    -0.17
    POSITIVE LOGITS
    ALLY
    0.59
    ally
    0.52
    ity
    0.40
    ITY
    0.32
    amente
    0.31
    all
    0.29
    ians
    0.28
    ities
    0.28
    ated
    0.26
    ian
    0.23
    Act Density 0.223%

    No Known Activations