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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or terminology related to data structures or protocols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     estimés
    -0.81
     Zend
    -0.76
     Zand
    -0.74
     Malabar
    -0.73
    Hast
    -0.71
     Gret
    -0.69
     Ши
    -0.68
    ar
    -0.66
     yore
    -0.66
    ên
    -0.66
    POSITIVE LOGITS
     CX
    1.29
    CX
    1.02
    cx
    0.98
     cx
    0.96
     RX
    0.82
     Cx
    0.82
     rx
    0.79
     Sulf
    0.77
    reactivex
    0.76
    gatsby
    0.76
    Act Density 0.007%

    No Known Activations