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

    Neuronpedia

    INDEX
    Explanations

    words ending with the suffix "-able" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.77
    n
    -0.76
    m
    -0.75
    ing
    -0.74
    N
    -0.64
    <eos>
    -0.64
    en
    -0.64
    X
    -0.64
    jspx
    -0.61
    T
    -0.61
    POSITIVE LOGITS
    izable
    1.21
    vable
    1.20
     myſelf
    1.18
     Efq
    1.17
     Theſe
    1.15
    urable
    1.09
     ―――――
    1.08
    chable
    1.08
     himſelf
    1.07
     ་་
    1.07
    Act Density 0.252%

    No Known Activations