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

    Neuronpedia

    INDEX
    Explanations

    terms associated with governance and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ape
    -0.18
    anton
    -0.15
    lfw
    -0.15
    oma
    -0.14
    oman
    -0.14
     OPTIONAL
    -0.14
    UTTON
    -0.14
     protagon
    -0.14
    illi
    -0.14
    elf
    -0.13
    POSITIVE LOGITS
    ê²Ģ
    0.16
    ìľ
    0.15
     Loch
    0.14
     Winning
    0.14
    ÂłkW
    0.14
     اذ
    0.14
    kte
    0.14
    osto
    0.14
    hey
    0.14
    -win
    0.13
    Act Density 0.039%

    No Known Activations