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

    Neuronpedia

    INDEX
    Explanations

    concepts related to expected events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingu
    -0.14
    (íģ¬ê¸°
    -0.14
    ±ä¹IJ
    -0.14
    .Îł
    -0.13
    .deb
    -0.13
    سÙĩ
    -0.13
    _logits
    -0.13
    ãĥ»ãĥ»ãĥ»↵↵
    -0.12
     EntityState
    -0.12
    -ar
    -0.12
    POSITIVE LOGITS
     if
    0.54
     If
    0.42
    if
    0.39
     is
    0.36
     IF
    0.35
     nếu
    0.35
     iff
    0.33
    	if
    0.33
     еÑģли
    0.32
     it
    0.32
    Act Density 0.093%

    No Known Activations