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

    Neuronpedia

    INDEX
    Explanations

    references to the word "what" across various contexts

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

    than what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.71
     CreateTagHelper
    -0.58
    principalColumn
    -0.57
    IUrlHelper
    -0.55
    ftagPool
    -0.55
     صوتيه
    -0.52
    oa̍t
    -0.50
    contentLoaded
    -0.49
     NSCoder
    -0.48
     الحره
    -0.47
    POSITIVE LOGITS
    trise
    0.44
    Hvad
    0.40
    ive
    0.39
    Cuál
    0.38
    use
    0.37
    vam
    0.37
    ve
    0.36
     Excessive
    0.36
     oat
    0.36
     levure
    0.36
    Act Density 0.017%

    No Known Activations