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

    Neuronpedia

    INDEX
    Explanations

    attends to numerical tokens from contextual tokens that reference a previous state or definition

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.06
    2:0.08
    3:0.11
    4:0.10
    5:0.04
    6:0.29
    7:0.22
    Negative Logits
     خارجية
    -0.38
     visuales
    -0.34
    tualmente
    -0.34
     recenti
    -0.34
    assertIs
    -0.33
    IntoConstraints
    -0.33
     *)__
    -0.32
     rouges
    -0.32
    PerformLayout
    -0.32
    ývá
    -0.31
    POSITIVE LOGITS
     Мексичка
    0.38
    AccessorTable
    0.36
    曖昧さ回避
    0.35
    Groetjes
    0.35
    AndEndTag
    0.34
    Twas
    0.33
    ItemBackground
    0.32
     '\\;'
    0.31
    였다
    0.30
    tonode
    0.30
    Act Density 5.093%

    No Known Activations