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

    Neuronpedia

    INDEX
    Explanations

    proposals or recommendations put forward by individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proposals or suggestions being made

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chan
    -0.77
    xs
    -0.72
    oly
    -0.70
    xe
    -0.68
    pac
    -0.67
    xa
    -0.66
    lymp
    -0.66
    icka
    -0.64
    OME
    -0.63
    outer
    -0.62
    POSITIVE LOGITS
    rists
    0.73
     proposals
    0.72
    ilts
    0.72
    tains
    0.69
    姫
    0.68
    actionDate
    0.65
    osal
    0.64
    OSED
    0.63
     Tuls
    0.63
    Recommend
    0.63
    Act Density 0.020%

    No Known Activations