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

    Neuronpedia

    INDEX
    Explanations

    the term "hot" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ately
    -0.17
    idal
    -0.17
    oke
    -0.17
    aging
    -0.16
    qb
    -0.15
    abled
    -0.15
    068
    -0.15
    ials
    -0.15
    hy
    -0.15
    üstü
    -0.15
    POSITIVE LOGITS
    -hot
    0.30
    spots
    0.30
     hot
    0.26
    Hot
    0.25
    izontal
    0.25
    chk
    0.24
    shot
    0.24
     Hot
    0.24
    .hot
    0.23
    hot
    0.22
    Act Density 0.019%

    No Known Activations