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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "able," indicating a focus on capability or capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    able to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.76
     your
    -0.52
     the
    -0.46
     Schwartz
    -0.44
     Herbst
    -0.41
     Erickson
    -0.40
     its
    -0.40
     alongside
    -0.40
     these
    -0.39
     בח
    -0.39
    POSITIVE LOGITS
     able
    1.24
    Able
    1.10
     Able
    1.04
     unable
    0.90
    unable
    0.89
     Unable
    0.89
    Unable
    0.85
     Ability
    0.84
     capaces
    0.84
     capaz
    0.83
    Act Density 0.010%

    No Known Activations