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

    Neuronpedia

    INDEX
    Explanations

    the presence of the letter 'o' in various contexts or quantities

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

    variable o raised to powers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tracce
    -0.57
    ambilan
    -0.56
     interactiva
    -0.54
     sintética
    -0.53
     transcur
    -0.53
    felizmente
    -0.51
    ytale
    -0.51
     añad
    -0.51
     navideña
    -0.50
    GenerationType
    -0.49
    POSITIVE LOGITS
    O
    1.00
     O
    0.95
     o
    0.78
    o
    0.68
    OA
    0.68
    Oo
    0.66
    EO
    0.66
    eo
    0.65
    <bos>
    0.65
    orio
    0.64
    Act Density 0.080%

    No Known Activations