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

    Neuronpedia

    INDEX
    Explanations

    references to directories

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Kem
    -0.77
    Kem
    -0.77
    ists
    -0.75
     captains
    -0.75
     cref
    -0.68
     PFA
    -0.68
     HANS
    -0.68
     mika
    -0.67
    alist
    -0.66
     Utf
    -0.66
    POSITIVE LOGITS
     directory
    0.98
    DIRECTORY
    0.87
    Directory
    0.85
     DIRECTORY
    0.85
    directory
    0.83
     Directory
    0.81
    isDirectory
    0.76
     directories
    0.73
    ,$_
    0.72
    יצוני
    0.71
    Act Density 0.007%

    No Known Activations