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

    Neuronpedia

    INDEX
    Explanations

    references to specific storage capacities and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.78
    ĸļ
    -0.78
    andise
    -0.67
    ansen
    -0.67
    orical
    -0.65
    acus
    -0.64
     Foley
    -0.64
    ichita
    -0.64
    ority
    -0.64
     disadvant
    -0.63
    POSITIVE LOGITS
    bit
    0.89
    kHz
    0.87
     bytes
    0.83
    Bit
    0.82
    GB
    0.82
    384
    0.81
    Gb
    0.79
    kB
    0.75
    DD
    0.73
     integers
    0.72
    Act Density 0.041%

    No Known Activations