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

    Neuronpedia

    INDEX
    Explanations

    references to product launches or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.06
    2:0.08
    3:0.08
    4:0.04
    5:0.08
    6:0.04
    7:0.04
    8:0.18
    9:0.21
    10:0.08
    11:0.03
    Negative Logits
     sworn
    -1.26
     cler
    -1.18
     defeated
    -1.17
     murdered
    -1.16
    yll
    -1.16
     obe
    -1.15
    hya
    -1.13
     fing
    -1.13
    heastern
    -1.12
    eret
    -1.12
    POSITIVE LOGITS
    Launch
    1.59
    UNCH
    1.56
     Launch
    1.49
    Asia
    1.42
    MAP
    1.36
     crowdfunding
    1.34
    starter
    1.34
    EVA
    1.33
    romeda
    1.32
    AMD
    1.32
    Act Density 0.040%

    No Known Activations