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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proficiency in multiple languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lah
    -0.16
    mey
    -0.15
    uego
    -0.14
    moid
    -0.14
    oscopic
    -0.13
     zbo
    -0.13
    exact
    -0.13
    afort
    -0.13
    iked
    -0.13
     exact
    -0.13
    POSITIVE LOGITS
    iper
    0.15
    toDate
    0.15
    ê¶Į
    0.14
    .dispatcher
    0.14
    Hooks
    0.14
     trending
    0.14
    ACES
    0.14
    ÙĦÛĮت
    0.14
    вÑĸ
    0.14
    elder
    0.13
    Act Density 0.025%

    No Known Activations