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

    Neuronpedia

    INDEX
    Explanations

    words that suggest the capability or ability of objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    n
    -0.80
    m
    -0.77
    ing
    -0.77
    9
    -0.66
    es
    -0.64
    th
    -0.64
    T
    -0.63
     T
    -0.62
    2
    -0.62
    <eos>
    -0.61
    POSITIVE LOGITS
    izable
    1.36
    vable
    1.29
    urable
    1.23
    gable
    1.21
    chable
    1.20
    asable
    1.17
    able
    1.15
     Efq
    1.14
     Theſe
    1.13
    mountable
    1.11
    Act Density 0.323%

    No Known Activations