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

    Neuronpedia

    INDEX
    Explanations

    references to academic positions and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.05
    4:0.08
    5:0.02
    6:0.04
    7:0.24
    8:0.03
    9:0.04
    10:0.22
    11:0.12
    Negative Logits
     playlist
    -1.47
     slang
    -1.32
     Zombies
    -1.32
    Arcade
    -1.32
     listeners
    -1.30
    ッ
    -1.29
    黒
    -1.28
    オ
    -1.28
    Tube
    -1.27
    ーン
    -1.26
    POSITIVE LOGITS
     Theodore
    1.43
     reconstruct
    1.34
    inally
    1.32
     rejuven
    1.28
    ijah
    1.28
     reversible
    1.27
    edi
    1.25
    uctor
    1.25
     uncover
    1.24
    rex
    1.24
    Act Density 0.003%

    No Known Activations