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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts indicating similarity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tera
    -0.16
    bourne
    -0.15
    ãĥ³ãĤ¸
    -0.15
     $?
    -0.15
    amax
    -0.14
    uled
    -0.14
    yw
    -0.13
    ainless
    -0.13
    lio
    -0.13
     scre
    -0.13
    POSITIVE LOGITS
     unto
    0.20
     Ñģобой
    0.18
     what
    0.17
     ours
    0.17
     nhau
    0.16
     except
    0.16
     typical
    0.16
     ÑģобоÑİ
    0.16
     ded
    0.15
     earlier
    0.15
    Act Density 0.083%

    No Known Activations