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

    Neuronpedia

    INDEX
    Explanations

    structured document elements and HTML tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.05
    2:0.07
    3:0.11
    4:0.04
    5:0.15
    6:0.20
    7:0.02
    8:0.05
    9:0.05
    10:0.06
    11:0.10
    Negative Logits
    hered
    -1.58
    ignt
    -1.47
    bery
    -1.45
    orporated
    -1.28
     hereditary
    -1.27
     annexation
    -1.27
     "$:/
    -1.27
    ghai
    -1.26
    yip
    -1.25
     bronze
    -1.19
    POSITIVE LOGITS
     sidx
    1.81
    repeat
    1.51
    talk
    1.48
     }}
    1.48
    >:
    1.35
    upe
    1.29
     EVENTS
    1.29
    aminer
    1.27
    Elsewhere
    1.26
    emphasis
    1.26
    Act Density 0.001%

    No Known Activations