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

    Neuronpedia

    INDEX
    Explanations

    phrases related to add-ons or additional features

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥª
    -0.81
    TPS
    -0.73
    OTH
    -0.71
    è¦ļéĨĴ
    -0.71
    RESULTS
    -0.70
    å°Ĩ
    -0.70
    Tex
    -0.70
     Annotations
    -0.69
    wake
    -0.68
    States
    -0.68
    POSITIVE LOGITS
    etheless
    1.16
    coming
    1.07
    itored
    0.95
    auts
    0.85
     behalf
    0.85
     arrival
    0.83
    nect
    0.83
    slaught
    0.81
    essee
    0.79
    etime
    0.78
    Act Density 0.040%

    No Known Activations