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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to belief and self-reflection

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

    Punctuation (, ;) followed by certain words

    np_acts-logits-general · gemini-2.0-flash

    completions and factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rieved
    -0.53
    abetes
    -0.53
     dispensation
    -0.52
     henvisninger
    -0.51
    TagMode
    -0.51
     häufigsten
    -0.49
     wireType
    -0.49
    ])));
    -0.49
    labus
    -0.48
    Datuak
    -0.48
    POSITIVE LOGITS
     factor
    0.66
     factors
    0.60
    idemia
    0.59
    factor
    0.58
     setOpen
    0.58
    րջ
    0.57
     تضيفلها
    0.57
    Factor
    0.57
    factors
    0.55
    因素
    0.54
    Act Density 0.404%

    No Known Activations