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

    Neuronpedia

    INDEX
    Explanations

    names, particularly of people and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.23
    1:0.01
    2:0.09
    3:0.09
    4:0.06
    5:0.02
    6:0.03
    7:0.02
    8:0.09
    9:0.11
    10:0.11
    11:0.10
    Negative Logits
    oaded
    -2.12
    sylv
    -1.78
    20439
    -1.56
    arah
    -1.40
    SourceFile
    -1.30
    INC
    -1.29
    PDF
    -1.29
    ctory
    -1.27
    Synopsis
    -1.24
    pedia
    -1.24
    POSITIVE LOGITS
    ;
    1.41
     etc
    1.41
     QC
    1.30
     Jr
    1.24
     Immun
    1.22
     HAL
    1.21
     respectively
    1.18
     profiling
    1.18
    ;"
    1.16
     ATF
    1.15
    Act Density 0.063%

    No Known Activations