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

    Neuronpedia

    INDEX
    Explanations

    phrases related to informality and unexpectedly detailed descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WARE
    -0.17
    metros
    -0.16
    ruba
    -0.15
    elli
    -0.15
    ylland
    -0.14
    ÑıÑĤелÑĮ
    -0.14
    /left
    -0.14
    emaakt
    -0.13
    (æĹ¥
    -0.13
    æľºåħ³
    -0.13
    POSITIVE LOGITS
    aturdays
    0.16
    appen
    0.15
     Bis
    0.14
    üc
    0.14
    ochen
    0.14
     Od
    0.13
    ipt
    0.13
     od
    0.13
    <
    0.13
    alu
    0.13
    Act Density 0.320%

    No Known Activations