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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their context within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ings
    -0.18
    redi
    -0.16
    ain
    -0.15
    ecom
    -0.14
    uario
    -0.14
    ãģ¨ãģĵãĤį
    -0.14
    orch
    -0.14
     Tits
    -0.14
    nik
    -0.14
    oid
    -0.14
    POSITIVE LOGITS
    âĢ³
    0.22
    ìĦł
    0.20
    teenth
    0.20
    teen
    0.20
    th
    0.18
    WD
    0.18
    ãģĦãĤĭ
    0.17
    444
    0.17
    thane
    0.17
    âĢ²
    0.16
    Act Density 0.178%

    No Known Activations