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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical discussions and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.11
    3:0.15
    4:0.11
    5:0.08
    6:0.02
    7:0.06
    8:0.08
    9:0.09
    10:0.13
    11:0.08
    Negative Logits
     contrasted
    -1.13
     divided
    -1.13
    cum
    -1.11
     pitted
    -1.11
     divides
    -1.09
     distinguishes
    -1.05
     greeted
    -1.05
     dividing
    -1.03
     1830
    -1.01
     Gallup
    -1.01
    POSITIVE LOGITS
    )).
    1.66
    ]).
    1.48
    $.
    1.48
    .).
    1.40
    }.
    1.37
     :)
    1.35
    ��
    1.34
    Reloaded
    1.33
    ?).
    1.32
     ;)
    1.30
    Act Density 0.873%

    No Known Activations