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

    Neuronpedia

    INDEX
    Explanations

    elements of social commentary regarding cultural perceptions or stereotypes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Meksiku
    -1.18
     تانيه
    -1.10
     ་་
    -1.08
     ſind
    -1.06
    Personendaten
    -1.06
    jmniej
    -1.04
    ^(@)
    -1.03
    NUMX
    -1.01
     pinulongan
    -1.01
     doubtnut
    -1.00
    POSITIVE LOGITS
    -
    0.61
    *
    0.60
    \
    0.60
     E
    0.58
    ↵
    0.56
    E
    0.55
    m
    0.55
    v
    0.54
    ,
    0.52
    2
    0.52
    Act Density 0.615%

    No Known Activations