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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceb
    -0.15
    _accessible
    -0.15
    çķ
    -0.15
    ormal
    -0.15
    adh
    -0.14
    abolic
    -0.14
    alia
    -0.14
    IAL
    -0.13
    uchs
    -0.13
    ialias
    -0.13
    POSITIVE LOGITS
    ilon
    0.17
    aging
    0.17
    dust
    0.17
     Ple
    0.15
    illac
    0.15
    wards
    0.14
    terr
    0.14
    porter
    0.14
    Sure
    0.14
    LETED
    0.14
    Act Density 0.093%

    No Known Activations