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

    Neuronpedia

    INDEX
    Explanations

    terms related to excitement and enjoyment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ess
    -0.28
    elli
    -0.27
    ell
    -0.27
    yonel
    -0.27
    ed
    -0.26
    ex
    -0.26
    em
    -0.25
    elle
    -0.25
    es
    -0.23
    el
    -0.23
    POSITIVE LOGITS
    abyrinth
    0.26
    iferay
    0.25
    ateral
    0.24
    abyrin
    0.23
    ts
    0.22
    ounge
    0.22
    ution
    0.22
    orraine
    0.21
    izabeth
    0.21
    ty
    0.21
    Act Density 0.580%

    No Known Activations