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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and entities mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.04
    2:0.08
    3:0.16
    4:0.14
    5:0.04
    6:0.02
    7:0.05
    8:0.04
    9:0.03
    10:0.22
    11:0.03
    Negative Logits
    imum
    -2.29
     beginner
    -2.26
    phthal
    -2.18
    isite
    -2.16
    isable
    -2.15
    remote
    -2.15
     species
    -2.14
    isoft
    -2.12
    existent
    -2.09
    functional
    -2.09
    POSITIVE LOGITS
     disagreed
    3.04
     apologized
    2.96
     testified
    2.84
     VIDEOS
    2.82
     spoke
    2.81
     cheered
    2.71
     UNCLASSIFIED
    2.70
     disagrees
    2.69
     refuted
    2.69
     objected
    2.68
    Act Density 0.427%

    No Known Activations