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

    Neuronpedia

    INDEX
    Explanations

    references to programming or technical specifications related to binary formats

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.75
    oprecip
    -0.69
    thday
    -0.65
    roba
    -0.65
     pleaſure
    -0.65
    éphane
    -0.63
     deserts
    -0.63
    phinx
    -0.62
    getSeconds
    -0.61
     soups
    -0.61
    POSITIVE LOGITS
    bpf
    1.87
    BPF
    1.33
     disambiguazione
    0.59
     zeichnet
    0.57
    :✨
    0.56
    '.
    0.55
    Lihat
    0.55
    an
    0.54
    uxxxx
    0.54
    Comun
    0.53
    Act Density 0.011%

    No Known Activations