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

    Neuronpedia

    INDEX
    Explanations

    references to selection processes or decision-making entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.07
    3:0.06
    4:0.26
    5:0.05
    6:0.03
    7:0.18
    8:0.02
    9:0.04
    10:0.10
    11:0.09
    Negative Logits
    ctrl
    -1.55
    cessive
    -1.55
    icably
    -1.54
    acerb
    -1.54
    artifacts
    -1.53
    chwitz
    -1.52
    agra
    -1.52
    vable
    -1.51
    ront
    -1.50
    amacare
    -1.50
    POSITIVE LOGITS
     insiders
    1.91
     audience
    1.84
     onlook
    1.81
     producers
    1.79
     reviewers
    1.79
     recipients
    1.70
     audiences
    1.70
     interviewer
    1.69
     consortium
    1.66
     responders
    1.66
    Act Density 0.001%

    No Known Activations