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

    Neuronpedia

    INDEX
    Explanations

    information related to news articles or updates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to finances or monetary topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.09
    2:0.08
    3:0.09
    4:0.19
    5:0.15
    6:0.08
    7:0.02
    8:0.04
    9:0.09
    10:0.06
    11:0.02
    Negative Logits
    rouse
    -1.38
     Woods
    -1.35
     Tele
    -1.32
     ''
    -1.30
     Peters
    -1.26
     Judd
    -1.24
     Thomson
    -1.21
    Newsletter
    -1.16
    Roaming
    -1.16
     occasionally
    -1.14
    POSITIVE LOGITS
    miah
    1.95
    ::::::::
    1.75
    �
    1.72
    �
    1.72
    PDATE
    1.64
    ️
    1.61
     tremend
    1.55
    anwhile
    1.52
    ��
    1.50
     srf
    1.50
    Act Density 0.031%

    No Known Activations