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

    Neuronpedia

    INDEX
    Explanations

    expressions of self-pride and ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ney
    -0.15
    usercontent
    -0.15
    ses
    -0.14
     atom
    -0.14
    æĻ
    -0.14
    atomic
    -0.14
    cks
    -0.13
     Insecta
    -0.13
    orama
    -0.13
    å§
    -0.13
    POSITIVE LOGITS
    etty
    0.17
    .generated
    0.16
    osti
    0.16
    owa
    0.15
    ldr
    0.14
    oard
    0.14
    era
    0.14
    erer
    0.14
    ERA
    0.14
    åī¯
    0.14
    Act Density 0.003%

    No Known Activations