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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating terms and conditions of agreements

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

    "In the" preceded by punctuation

    np_acts-logits-general · gemini-2.0-flash

    in the event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MENAFN
    -0.61
    "{\
    -0.58
     Amongst
    -0.58
    ]='\
    -0.55
    ymal
    -0.55
     nakalista
    -0.54
    hetically
    -0.54
    oraz
    -0.54
     Rather
    -0.54
     Among
    -0.53
    POSITIVE LOGITS
     connection
    0.52
     furtherance
    0.51
     WRITING
    0.51
     writing
    0.51
     ArrayAdapter
    0.50
     light
    0.47
     صوتيه
    0.46
    AndEndTag
    0.46
     accordance
    0.46
     étrangères
    0.46
    Act Density 0.514%

    No Known Activations