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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of understanding or desire for accountability

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "ľ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     targeted
    -0.86
     pigeon
    -0.83
     clitor
    -0.80
     pyramid
    -0.75
     tyres
    -0.72
     relative
    -0.72
     envelope
    -0.70
     eyeb
    -0.70
     favor
    -0.70
     favour
    -0.69
    POSITIVE LOGITS
    ï¸ı
    1.45
    ï¸
    1.06
    However
    1.05
    Therefore
    1.01
    ICE
    0.97
    Roberts
    0.97
    âĶĢâĶĢâĶĢâĶĢ
    0.97
    RELATED
    0.97
    Unfortunately
    0.96
    Likewise
    0.94
    Act Density 0.145%

    No Known Activations