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

    Neuronpedia

    INDEX
    Explanations

    attends to numerical tokens from tokens that signify years in parentheses

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.14
    2:0.11
    3:0.09
    4:0.09
    5:0.03
    6:0.14
    7:0.28
    Negative Logits
     initComponents
    -0.28
    Obras
    -0.25
    endphp
    -0.25
    SourceChecksum
    -0.25
    newArrayList
    -0.25
     Ola
    -0.24
    MergeFrom
    -0.24
    醐
    -0.24
     PZ
    -0.23
    ométrie
    -0.23
    POSITIVE LOGITS
    ThroughAttribute
    0.38
     Roskov
    0.38
     فريبيس
    0.37
     itſelf
    0.37
    Xna
    0.35
     Mard
    0.34
     Majefty
    0.34
     خارجية
    0.33
    AccessorTable
    0.33
     defStyle
    0.32
    Act Density 0.240%

    No Known Activations