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

    Neuronpedia

    INDEX
    Explanations

    mentions of recorded tapes or videos related to controversial subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.07
    4:0.06
    5:0.06
    6:0.03
    7:0.14
    8:0.03
    9:0.04
    10:0.32
    11:0.09
    Negative Logits
    ategor
    -1.79
     concess
    -1.78
    advant
    -1.70
     specialization
    -1.69
     denomin
    -1.66
     GCC
    -1.62
     vector
    -1.62
     grep
    -1.57
    Ability
    -1.57
     docker
    -1.56
    POSITIVE LOGITS
     tapes
    2.93
     recordings
    2.63
     videot
    2.41
     taped
    2.41
     tape
    2.12
     recording
    2.02
     interrogation
    1.83
     incrim
    1.74
     allegations
    1.73
     wiret
    1.71
    Act Density 0.004%

    No Known Activations