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

    Neuronpedia

    INDEX
    Explanations

    mentions of directories in a file system or project structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acting
    -0.84
    acted
    -0.82
    akening
    -0.78
    pter
    -0.76
    practice
    -0.74
    terson
    -0.73
    oria
    -0.71
    rained
    -0.70
     damned
    -0.66
    uca
    -0.65
    POSITIVE LOGITS
    abases
    0.87
     directories
    0.84
    =/
    0.83
     "/
    0.82
     directory
    0.82
     hierarchy
    0.81
     Contents
    0.81
     travers
    0.80
     descriptor
    0.79
     '/
    0.77
    Act Density 0.005%

    No Known Activations