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

    Neuronpedia

    INDEX
    Explanations

    attends to the final punctuation mark from various subsequent tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.20
    1:0.17
    2:0.12
    3:0.15
    4:0.13
    5:0.04
    6:0.07
    7:0.08
    Negative Logits
     ujednoznacz
    -0.34
    ddots
    -0.34
    ném
    -0.26
    اتر
    -0.26
     kasarigan
    -0.26
    -0.26
    SOM
    -0.26
    newValue
    -0.25
    minecraft
    -0.25
     getInstance
    -0.25
    POSITIVE LOGITS
     HasFactory
    0.37
    ContentAlignment
    0.37
     jsPsych
    0.36
    AndEndTag
    0.33
    expandindo
    0.33
     beginnetje
    0.33
     protoimpl
    0.32
    RenderAtEndOf
    0.31
     unknownFields
    0.31
     NSCoder
    0.30
    Act Density 0.362%

    No Known Activations