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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political comments and speeches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.04
    3:0.10
    4:0.06
    5:0.07
    6:0.03
    7:0.03
    8:0.06
    9:0.08
    10:0.31
    11:0.11
    Negative Logits
     extermin
    -1.58
    surv
    -1.56
     [&
    -1.56
     PCB
    -1.55
     LTD
    -1.45
     CRC
    -1.40
    MpServer
    -1.40
     strugg
    -1.40
     IPM
    -1.39
     upstream
    -1.37
    POSITIVE LOGITS
    Asked
    1.58
     Asked
    1.57
    Said
    1.55
    Note
    1.47
    uphem
    1.46
     Kimmel
    1.44
     joked
    1.44
    CNN
    1.43
    Foreign
    1.42
    Repeat
    1.37
    Act Density 0.139%

    No Known Activations