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

    Neuronpedia

    INDEX
    Explanations

    occurrences of parentheses and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elin
    -0.15
     Beled
    -0.15
    ProgressHUD
    -0.14
    uko
    -0.14
    ilece
    -0.13
    precated
    -0.13
    ãĥªãĥ³ãĤ°
    -0.13
    ponsored
    -0.13
    renc
    -0.13
     Rac
    -0.13
    POSITIVE LOGITS
    ands
    0.15
    agan
    0.15
    etsk
    0.15
    stral
    0.15
    usz
    0.14
    íĤ¹
    0.14
    -)
    0.14
     Stef
    0.14
     mostly
    0.13
     teil
    0.13
    Act Density 0.074%

    No Known Activations