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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical data and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.10
    3:0.13
    4:0.10
    5:0.02
    6:0.06
    7:0.28
    8:0.02
    9:0.03
    10:0.08
    11:0.09
    Negative Logits
    venge
    -1.54
    ihil
    -1.53
    oct
    -1.53
    except
    -1.49
    arse
    -1.47
     Contest
    -1.45
     extortion
    -1.41
     FIGHT
    -1.40
    quad
    -1.39
     uncond
    -1.39
    POSITIVE LOGITS
     gems
    1.81
    sites
    1.71
     glance
    1.50
     gem
    1.46
     snippets
    1.44
    giene
    1.42
     VIDEOS
    1.40
     passages
    1.40
    ggles
    1.39
     reputable
    1.38
    Act Density 0.003%

    No Known Activations