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

    Neuronpedia

    INDEX
    Explanations

    references to time and events that are contingent on prior occurrences

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

    prior to an event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.56
    Parcelize
    -0.56
    :✨
    -0.55
    səhifə
    -0.54
     increí
    -0.54
    enumi
    -0.52
    enumii
    -0.51
     emprunt
    -0.51
     fevere
    -0.51
     AssemblyVersion
    -0.51
    POSITIVE LOGITS
     before
    0.73
    before
    0.66
    Before
    0.60
    BEFORE
    0.59
     Before
    0.59
     BEFORE
    0.59
     πριν
    0.48
     sebelum
    0.47
     voordat
    0.43
     antes
    0.42
    Act Density 0.031%

    No Known Activations