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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe unverified claims or contentious statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.01
    2:0.07
    3:0.26
    4:0.02
    5:0.09
    6:0.03
    7:0.08
    8:0.03
    9:0.05
    10:0.16
    11:0.08
    Negative Logits
    secondary
    -1.10
    anners
    -1.03
    hero
    -1.03
    rals
    -1.00
    %;
    -0.98
    nikov
    -0.97
    practice
    -0.97
    >.
    -0.95
    selection
    -0.95
    anking
    -0.94
    POSITIVE LOGITS
    SPONSORED
    1.10
     incidentally
    1.04
     anat
    1.00
     presumably
    0.99
     Brach
    0.96
     ought
    0.96
     translates
    0.95
    ��
    0.93
    ieri
    0.92
     lacks
    0.92
    Act Density 0.272%

    No Known Activations