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

    Neuronpedia

    INDEX
    Explanations

    references to different types or categories of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cifix
    -1.02
     Roach
    -0.94
    ViewFeatures
    -0.91
     חיצוניים
    -0.86
     Geller
    -0.86
    AddTagHelper
    -0.84
    Дереккөздер
    -0.83
    bleven
    -0.81
    ectomy
    -0.79
    axel
    -0.79
    POSITIVE LOGITS
     Kind
    1.38
     KIND
    1.38
    kind
    1.36
     kind
    1.36
    Kind
    1.35
    KIND
    1.26
     kinds
    1.15
    kinds
    1.14
    Kinds
    1.13
     sort
    1.11
    Act Density 0.084%

    No Known Activations