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

    Neuronpedia

    INDEX
    Explanations

    attends to the "since" token from arbitrary tokens that appear later in the sequence

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.17
    2:0.09
    3:0.09
    4:0.07
    5:0.04
    6:0.09
    7:0.27
    Negative Logits
    StoryboardSegue
    -0.33
    libft
    -0.31
    extAlignment
    -0.28
    wpi
    -0.28
    qrstuvwxyz
    -0.28
    iastes
    -0.27
    VersionUID
    -0.27
    Handlung
    -0.27
     AssemblyProduct
    -0.26
    ArgsConstructor
    -0.26
    POSITIVE LOGITS
    .*")]
    0.29
     OFDb
    0.28
    ]")]
    0.28
     nakalista
    0.27
     >",
    0.26
     Rer
    0.26
     Censo
    0.26
     ")";
    0.26
    település
    0.25
     Hays
    0.25
    Act Density 0.019%

    No Known Activations