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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" or similar referential phrases indicating specific examples

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

    these expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intios
    -0.40
     Signalez
    -0.40
    addLast
    -0.39
     bus
    -0.38
     debate
    -0.38
     VEGET
    -0.37
    狩
    -0.37
     cor
    -0.37
     device
    -0.36
     animal
    -0.36
    POSITIVE LOGITS
    Архівовано
    0.64
    NameInMap
    0.57
    webElementXpaths
    0.55
     للمعارف
    0.54
     serupa
    0.53
    tagHelperRunner
    0.52
    ⓧ
    0.50
     semblables
    0.50
    webElement
    0.49
    Aiheesta
    0.47
    Act Density 0.016%

    No Known Activations