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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rim
    -0.16
    sets
    -0.15
    leigh
    -0.14
    ables
    -0.14
    emer
    -0.14
    ults
    -0.14
    stu
    -0.14
    ħĮ
    -0.14
    ograms
    -0.14
    fts
    -0.14
    POSITIVE LOGITS
     among
    0.25
     amongst
    0.21
     example
    0.21
     step
    0.21
     hell
    0.20
     reason
    0.19
     those
    0.18
    among
    0.18
     area
    0.18
     heck
    0.18
    Act Density 0.032%

    No Known Activations