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

    Neuronpedia

    INDEX
    Explanations

    questions and conditional phrases related to uncertainty about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.06
    2:0.03
    3:0.15
    4:0.05
    5:0.24
    6:0.07
    7:0.04
    8:0.06
    9:0.11
    10:0.04
    11:0.04
    Negative Logits
    AppData
    -1.92
    bin
    -1.89
     Baseball
    -1.87
    oplan
    -1.81
    Area
    -1.78
     Miner
    -1.75
    Merc
    -1.72
    Base
    -1.71
    Mine
    -1.70
    artment
    -1.69
    POSITIVE LOGITS
    EStream
    2.20
     advoc
    2.12
     ratification
    1.94
     encour
    1.90
    authent
    1.88
     reclaimed
    1.88
    egal
    1.84
     compliments
    1.84
    CONCLUS
    1.84
    uador
    1.81
    Act Density 0.000%

    No Known Activations