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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate statistical trends or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jes
    -0.16
    AINS
    -0.15
    oci
    -0.15
    aji
    -0.14
    ains
    -0.14
     jÃŃ
    -0.14
    ationale
    -0.13
    Doctrine
    -0.13
    ette
    -0.13
     soci
    -0.13
    POSITIVE LOGITS
    bolt
    0.15
    illin
    0.15
    иÑĩа
    0.14
     Bans
    0.14
    vap
    0.14
    readcrumb
    0.14
    ENCH
    0.14
    onde
    0.13
    ETCH
    0.13
    osen
    0.13
    Act Density 0.029%

    No Known Activations