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

    Neuronpedia

    INDEX
    Explanations

    phrases related to enabling or assisting others, potentially in a supportive or empowering way

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to technology and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.51
    hra
    -0.50
    hov
    -0.49
    cknowled
    -0.48
    anwhile
    -0.47
    cussion
    -0.45
    Hor
    -0.44
     partName
    -0.44
    ggles
    -0.43
     denotes
    -0.43
    POSITIVE LOGITS
     someday
    0.61
     toget
    0.58
     anymore
    0.53
     undet
    0.51
     vulner
    0.48
    agra
    0.47
     kitchens
    0.47
     idols
    0.46
     Saiyan
    0.46
    .</
    0.45
    Act Density 5.575%

    No Known Activations