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

    Neuronpedia

    INDEX
    Explanations

    temporal references in relation to significant events

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

    that often come before other words

    np_acts-logits-general · gemini-2.0-flash

    time indicators like weeks and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "):
    -0.82
     autorytatywna
    -0.80
    '):
    -0.80
     المعيارى
    -0.79
    ="">
    -0.70
     ")[
    -0.70
    principalColumn
    -0.69
    ſelves
    -0.68
     Diſ
    -0.68
     Administrativna
    -0.67
    POSITIVE LOGITS
     we
    0.96
    ,
    0.89
     when
    0.80
     there
    0.68
     they
    0.65
     during
    0.61
    During
    0.60
    When
    0.59
     he
    0.59
     you
    0.57
    Act Density 0.282%

    No Known Activations