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

    Neuronpedia

    INDEX
    Explanations

    references to types of cooking, particularly those involving char and grilled techniques

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

    chartist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zbęd
    -0.49
     }>
    -0.47
    ese
    -0.47
    ebs
    -0.46
     Peabody
    -0.45
     Veda
    -0.45
    )|^{
    -0.45
    ests
    -0.44
    mergeFrom
    -0.44
     Nelly
    -0.43
    POSITIVE LOGITS
     Char
    1.06
    Char
    1.03
     char
    0.96
     CHAR
    0.93
    CHAR
    0.90
    char
    0.88
     chars
    0.72
    CharField
    0.71
     Schar
    0.69
    chars
    0.67
    Act Density 0.005%

    No Known Activations