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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating further development or additional information

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating continuation or additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -0.95
    bows
    -0.92
    encers
    -0.82
    ences
    -0.81
    images
    -0.80
    ographs
    -0.79
    casts
    -0.76
    ENTS
    -0.76
    masters
    -0.75
    rooms
    -0.75
    POSITIVE LOGITS
     layer
    1.01
     complication
    0.96
     step
    0.93
     option
    0.92
     subset
    0.90
     caveat
    0.90
     workaround
    0.88
     loophole
    0.85
     dose
    0.85
     handful
    0.83
    Act Density 0.124%

    No Known Activations