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

    Neuronpedia

    INDEX
    Explanations

    terms related to official announcements or directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ides
    -0.20
    aver
    -0.16
    Configurer
    -0.15
    ÅĻeb
    -0.15
    à¸ĸ
    -0.15
    æ¯ķ
    -0.15
    lej
    -0.14
    à¯įà®
    -0.14
    orton
    -0.14
    inton
    -0.14
    POSITIVE LOGITS
     Zub
    0.17
    ñana
    0.16
    gang
    0.16
    732
    0.15
    ooke
    0.15
    antee
    0.14
    ited
    0.14
    lip
    0.14
    anine
    0.14
    code
    0.14
    Act Density 0.022%

    No Known Activations