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

    Neuronpedia

    INDEX
    Explanations

    structures for organizing various types of information, particularly in academic or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vla
    -0.16
    rana
    -0.15
    yntax
    -0.15
    swick
    -0.15
    .appspot
    -0.14
    ække
    -0.14
    abant
    -0.14
     IMPLIED
    -0.14
    ecided
    -0.14
    smouth
    -0.14
    POSITIVE LOGITS
     acronym
    0.25
    stands
    0.25
    abbreviation
    0.24
     abbreviation
    0.21
     stands
    0.19
    ¥
    0.18
     ac
    0.17
    letters
    0.16
     MacDonald
    0.16
    pron
    0.15
    Act Density 0.091%

    No Known Activations