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

    Neuronpedia

    INDEX
    Explanations

    references to cultural critiques and philosophical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quez
    -0.17
    ãģĴ
    -0.16
     we
    -0.15
    hangi
    -0.14
    umm
    -0.14
    878
    -0.14
    inho
    -0.14
    bsolute
    -0.13
    abbit
    -0.13
     Mein
    -0.13
    POSITIVE LOGITS
    ycastle
    0.17
    ozem
    0.14
    irler
    0.14
    ê³Ħíļį
    0.14
    654
    0.14
     Sok
    0.14
    andal
    0.14
     spir
    0.13
    untime
    0.13
     ç
    0.13
    Act Density 0.000%

    No Known Activations