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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote high recognition or popularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owi
    -0.16
    igi
    -0.16
     ones
    -0.15
     defaultMessage
    -0.15
    urgeon
    -0.14
    umpt
    -0.14
    ÂĽ
    -0.14
    .Metro
    -0.14
    olle
    -0.14
     Balt
    -0.13
    POSITIVE LOGITS
    IDER
    0.16
    ثر
    0.14
    peater
    0.14
    ä»Ķ
    0.13
    quier
    0.13
     tim
    0.13
    heard
    0.13
    avras
    0.13
     Mean
    0.13
     Sev
    0.13
    Act Density 0.042%

    No Known Activations