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

    Neuronpedia

    INDEX
    Explanations

    phrases containing variations of the word "who."

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

    "Who" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    who followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.54
    ngrx
    -0.49
     esterni
    -0.48
    COUVER
    -0.48
    verständlich
    -0.47
    NameInMap
    -0.46
    Eloquent
    -0.46
    下一页
    -0.46
    ある
    -0.45
    ngdoc
    -0.44
    POSITIVE LOGITS
     might
    0.86
    TagMode
    0.77
     OTHERWISE
    0.74
     magari
    0.72
     aren
    0.72
    oped
    0.70
     mattered
    0.70
     MIGHT
    0.68
     وتسجيلات
    0.68
    oping
    0.67
    Act Density 0.162%

    No Known Activations