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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating financial or legal status and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izr
    -0.18
    unden
    -0.16
    kil
    -0.15
    obl
    -0.15
    aucoup
    -0.15
    unde
    -0.15
    ÑĥÑĢн
    -0.15
    dds
    -0.15
    etro
    -0.14
    307
    -0.14
    POSITIVE LOGITS
    cess
    0.14
    LY
    0.14
     Eisen
    0.14
    Tap
    0.13
    GRE
    0.13
    LAT
    0.13
    itia
    0.13
     pozdÄĽ
    0.13
    تد
    0.13
    zig
    0.13
    Act Density 0.000%

    No Known Activations