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

    Neuronpedia

    INDEX
    Explanations

    references to legal and political matters

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

    mentions of legal terminology and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.02
    2:0.04
    3:0.11
    4:0.05
    5:0.11
    6:0.04
    7:0.06
    8:0.17
    9:0.05
    10:0.12
    11:0.06
    Negative Logits
    rama
    -1.01
    rawdownloadcloneembedreportprint
    -1.01
    Beat
    -1.00
    enes
    -1.00
     cleaners
    -0.99
     Athlet
    -0.98
     Munich
    -0.96
    )=
    -0.94
     vitamins
    -0.93
    encer
    -0.92
    POSITIVE LOGITS
    entry
    1.12
    �
    1.07
     guiName
    1.05
    ��
    1.02
    ares
    1.01
    Rule
    0.98
    ofi
    0.97
    illary
    0.96
    �
    0.95
    SPONSORED
    0.95
    Act Density 0.117%

    No Known Activations