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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing significant news or stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.16
    3:0.11
    4:0.08
    5:0.03
    6:0.13
    7:0.08
    8:0.08
    9:0.05
    10:0.13
    11:0.07
    Negative Logits
    ּ
    -1.66
    FTWARE
    -1.56
     monog
    -1.45
     Sigma
    -1.40
     Alley
    -1.39
    lyak
    -1.34
    WAY
    -1.32
    ibly
    -1.31
     Velvet
    -1.30
    dit
    -1.28
    POSITIVE LOGITS
     IMAGES
    1.49
    hani
    1.48
    theme
    1.40
    bleacher
    1.36
    relevant
    1.31
     hr
    1.27
     illuminate
    1.26
     });
    1.23
     consume
    1.23
     pulse
    1.22
    Act Density 0.001%

    No Known Activations