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

    Neuronpedia

    INDEX
    Explanations

    details related to criminal activities and their legal repercussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.02
    2:0.05
    3:0.03
    4:0.05
    5:0.04
    6:0.21
    7:0.04
    8:0.07
    9:0.30
    10:0.02
    11:0.03
    Negative Logits
     Comet
    -3.81
    auga
    -3.75
     crater
    -3.69
     comet
    -3.65
     Surgery
    -3.51
     Haiti
    -3.50
    acteria
    -3.48
     helicopter
    -3.45
    Shell
    -3.45
    ouver
    -3.42
    POSITIVE LOGITS
    Rand
    11.77
     Rand
    11.54
     Randall
    8.30
    rand
    6.90
     RAND
    6.68
     Randolph
    6.45
     rand
    6.31
     Mund
    4.82
     Roth
    4.71
     libertarians
    4.65
    Act Density 0.005%

    No Known Activations