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

    Neuronpedia

    INDEX
    Explanations

    instances of editorials and their critical language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.06
    3:0.05
    4:0.07
    5:0.02
    6:0.06
    7:0.20
    8:0.03
    9:0.02
    10:0.35
    11:0.06
    Negative Logits
     smugglers
    -1.71
     handcuffs
    -1.63
     GPS
    -1.63
     snag
    -1.61
     extrad
    -1.60
     unlocks
    -1.58
    roo
    -1.58
     ZIP
    -1.56
     ATM
    -1.56
     rugged
    -1.56
    POSITIVE LOGITS
     Editorial
    2.12
    inion
    1.98
    NPR
    1.90
    Cola
    1.70
     reprinted
    1.58
    ovie
    1.58
    published
    1.57
     reacting
    1.56
    uggest
    1.54
     suppressing
    1.54
    Act Density 0.009%

    No Known Activations