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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of being able or capable of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ing
    -0.87
    n
    -0.82
    m
    -0.74
    es
    -0.71
    <eos>
    -0.69
    9
    -0.68
    th
    -0.66
    2
    -0.65
    <h2>
    -0.63
    ↵↵
    -0.62
    POSITIVE LOGITS
    izable
    1.34
    vable
    1.25
    urable
    1.24
    ^(@)
    1.22
     Theſe
    1.20
    chable
    1.19
     Efq
    1.19
     myſelf
    1.18
    asable
    1.17
     Jefus
    1.14
    Act Density 0.253%

    No Known Activations