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

    Neuronpedia

    INDEX
    Explanations

    mention of violent crimes and their perpetrators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.03
    2:0.03
    3:0.06
    4:0.03
    5:0.17
    6:0.01
    7:0.01
    8:0.04
    9:0.22
    10:0.17
    11:0.11
    Negative Logits
     domestically
    -1.00
    efeated
    -1.00
    odox
    -0.98
    otype
    -0.94
    oliberal
    -0.92
    izontal
    -0.89
    regate
    -0.89
    ogun
    -0.88
    ernels
    -0.87
    zsche
    -0.86
    POSITIVE LOGITS
     panicked
    1.08
    dding
    1.01
     retali
    0.99
     overheard
    0.96
     CONTIN
    0.95
     replied
    0.95
    Later
    0.93
     forwarded
    0.92
     intercepted
    0.92
     guessed
    0.91
    Act Density 1.977%

    No Known Activations