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

    Neuronpedia

    INDEX
    Explanations

    references to groups or categories of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.06
    3:0.05
    4:0.07
    5:0.05
    6:0.48
    7:0.02
    8:0.05
    9:0.03
    10:0.07
    11:0.04
    Negative Logits
     iod
    -1.37
     fuse
    -1.26
     reuse
    -1.25
    ovsky
    -1.24
     translation
    -1.24
    chieve
    -1.19
    draw
    -1.12
     texture
    -1.11
     supervision
    -1.11
     epis
    -1.10
    POSITIVE LOGITS
    iris
    1.50
     swayed
    1.48
     violated
    1.42
    esta
    1.42
    oi
    1.37
    oths
    1.37
    ppers
    1.35
    ��
    1.31
    swick
    1.31
    upper
    1.30
    Act Density 0.064%

    No Known Activations