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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loff
    -0.22
    orges
    -0.15
     Giang
    -0.14
     grips
    -0.14
    lop
    -0.14
     Barbar
    -0.14
    оза
    -0.14
    ãĥ³ãĥIJ
    -0.14
    ude
    -0.13
    ervers
    -0.13
    POSITIVE LOGITS
    awa
    0.17
    cli
    0.16
    agus
    0.16
    orna
    0.15
    ahn
    0.15
    ambi
    0.14
    ieron
    0.14
    ye
    0.14
    sti
    0.14
    idis
    0.14
    Act Density 0.010%

    No Known Activations