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

    Neuronpedia

    INDEX
    Explanations

    phrases related to promises or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    òi
    -0.16
    èĤĸ
    -0.16
    reve
    -0.16
    ernen
    -0.16
    âl
    -0.15
    ropolis
    -0.15
    agger
    -0.14
    ãĥ¼ãĥª
    -0.14
    atis
    -0.14
    hev
    -0.14
    POSITIVE LOGITS
    rac
    0.15
    eyim
    0.15
    arie
    0.14
    inue
    0.14
     Duy
    0.14
    _DRIVE
    0.14
     Curtis
    0.13
    ngr
    0.13
    @admin
    0.13
    047
    0.13
    Act Density 0.009%

    No Known Activations