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

    Neuronpedia

    INDEX
    Explanations

    recurrent phrases that reference specific moments in time

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

    "time" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    first time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -0.92
    IsContent
    -0.71
    WithIOException
    -0.71
     écoulé
    -0.69
    LLocation
    -0.65
     Administrativna
    -0.65
    elemField
    -0.63
    onViewCreated
    -0.63
    complexType
    -0.62
    UnsafeEnabled
    -0.62
    POSITIVE LOGITS
     chance
    0.65
    chance
    0.64
     visit
    0.60
    verständlich
    0.59
     layui
    0.59
    ebvre
    0.57
    Anytime
    0.56
    Chance
    0.54
    atimes
    0.54
    linde
    0.52
    Act Density 0.103%

    No Known Activations