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

    Neuronpedia

    INDEX
    Explanations

    instances of the string "in" and its variations, particularly in a technical or coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tory
    -0.66
    e
    -0.65
    es
    -0.62
    payable
    -0.60
    tale
    -0.57
    spacer
    -0.57
    gory
    -0.56
    a
    -0.56
    ctable
    -0.55
    ة
    -0.54
    POSITIVE LOGITS
    nnnn
    1.07
    nnn
    0.99
    ned
    0.92
     HIN
    0.88
    ning
    0.86
    nin
    0.86
     Zin
    0.81
    IN
    0.81
     незавершена
    0.79
    qin
    0.78
    Act Density 0.599%

    No Known Activations