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

    Neuronpedia

    INDEX
    Explanations

    expressions related to making decisions and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rg
    -0.17
    gcd
    -0.16
    iba
    -0.16
    olph
    -0.15
    adb
    -0.15
    rray
    -0.15
    ion
    -0.14
     cih
    -0.14
    SEP
    -0.14
    awai
    -0.14
    POSITIVE LOGITS
    usercontent
    0.19
    UILayout
    0.17
    assistant
    0.16
    ãĥ¼ãĥ«ãĥī
    0.15
    VERR
    0.15
    .sul
    0.15
    ека
    0.15
    kart
    0.15
    illin
    0.15
    inality
    0.14
    Act Density 0.294%

    No Known Activations