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

    Neuronpedia

    INDEX
    Explanations

    names of political figures and organizations

    oai_token-act-pair · gpt-3.5-turbo

    names and entities related to significant individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     POV
    -0.53
    IBLE
    -0.51
     PAN
    -0.50
     om
    -0.50
    ctive
    -0.50
     HDD
    -0.49
     Pok
    -0.48
     correction
    -0.47
    ORY
    -0.47
    shift
    -0.46
    POSITIVE LOGITS
    SPONSORED
    0.71
     respectively
    0.68
    interstitial
    0.65
    cffff
    0.59
     boycot
    0.59
     enshr
    0.58
    acus
    0.58
    akespeare
    0.58
    kefeller
    0.57
    reditary
    0.55
    Act Density 1.555%

    No Known Activations