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

    Neuronpedia

    INDEX
    Explanations

    phrases related to device features and performance issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zos
    -0.18
    gend
    -0.15
    ást
    -0.15
    ause
    -0.14
    ree
    -0.14
    жд
    -0.14
    zac
    -0.14
    adows
    -0.14
    duk
    -0.14
    isp
    -0.14
    POSITIVE LOGITS
     instead
    0.17
     Sabb
    0.16
    sap
    0.16
    768
    0.15
    leaning
    0.14
     Wel
    0.14
    ersh
    0.14
     Instead
    0.14
    erin
    0.14
     pand
    0.14
    Act Density 0.170%

    No Known Activations