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

    Neuronpedia

    INDEX
    Explanations

    words indicating a distinct or significant status or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑī
    -0.15
     craw
    -0.15
    isode
    -0.15
    orca
    -0.15
     маÑı
    -0.14
    ợ
    -0.14
    endoza
    -0.14
    ucks
    -0.14
    ãĥ¼ãĥijãĥ¼
    -0.14
     repl
    -0.14
    POSITIVE LOGITS
     thuá»Ļc
    0.16
     Mant
    0.15
    elm
    0.15
    ÅĻiv
    0.15
    rens
    0.14
    æķ
    0.14
     Kitt
    0.14
    ystone
    0.14
    ndx
    0.14
     lawmakers
    0.14
    Act Density 0.007%

    No Known Activations