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

    Neuronpedia

    INDEX
    Explanations

    statements that assert or clarify a condition or reasoning

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

    Comes before "that" followed by a clause

    np_acts-logits-general · gemini-2.0-flash

    clauses introduced by that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.12
    Personendaten
    -0.98
    OGND
    -0.96
    mybatisplus
    -0.84
    thâu
    -0.83
     Normdatei
    -0.83
     bezeichneter
    -0.82
     betweenstory
    -0.80
    endphp
    -0.80
    Vidite
    -0.78
    POSITIVE LOGITS
     While
    0.63
     If
    0.61
     He
    0.58
     When
    0.57
    :
    0.57
    While
    0.56
     you
    0.56
     if
    0.55
     when
    0.54
    If
    0.53
    Act Density 0.277%

    No Known Activations