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

    Neuronpedia

    INDEX
    Explanations

    file paths and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of slashes or path-like structures in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grimes
    -0.70
     intimid
    -0.67
     infiltr
    -0.65
    emouth
    -0.65
     Moody
    -0.64
     Democr
    -0.64
     Patton
    -0.63
     unsus
    -0.63
     DeV
    -0.62
     devils
    -0.62
    POSITIVE LOGITS
    ËĪ
    1.11
    usr
    1.07
    etc
    1.02
    upload
    0.96
    pmwiki
    0.94
    home
    0.93
    Flickr
    0.91
    ãĤ¨ãĥ«
    0.91
    Applications
    0.90
    \/\/
    0.89
    Act Density 0.041%

    No Known Activations