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

    Neuronpedia

    INDEX
    Explanations

    statements indicating observations or findings

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

    noted that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GenerationType
    -0.57
    Superclass
    -0.46
    Exclusive
    -0.46
    Reparto
    -0.45
     RU
    -0.45
    Inheritance
    -0.45
     ſte
    -0.44
     transf
    -0.44
     turbo
    -0.44
     puri
    -0.44
    POSITIVE LOGITS
     noted
    1.13
    noted
    1.04
     noting
    1.00
    Noted
    0.86
     note
    0.86
     señaló
    0.82
     noticing
    0.79
     señala
    0.77
     отмеча
    0.77
     remarquer
    0.77
    Act Density 0.030%

    No Known Activations