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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Aber" in various forms

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

    aberrant deviation or names like Aberforth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onViewCreated
    -0.51
     concha
    -0.50
    João
    -0.49
     Synagogue
    -0.48
    pios
    -0.47
    astero
    -0.47
    xelles
    -0.47
     flak
    -0.46
    quels
    -0.46
     Montevideo
    -0.46
    POSITIVE LOGITS
     aber
    1.82
     Aber
    1.38
    Aber
    1.31
    aber
    1.04
     però
    0.72
     jedoch
    0.71
     pero
    0.71
     But
    0.69
     but
    0.68
     aberration
    0.68
    Act Density 0.002%

    No Known Activations