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

    Neuronpedia

    INDEX
    Explanations

    issues surrounding social justice and inequality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scar
    -0.15
    anna
    -0.15
    Anywhere
    -0.15
     both
    -0.15
    999
    -0.14
     And
    -0.14
     scar
    -0.14
    olan
    -0.14
    ull
    -0.14
    311
    -0.14
    POSITIVE LOGITS
     بÙĦÚ©Ùĩ
    0.31
     sondern
    0.31
     sino
    0.27
     necessarily
    0.22
     nor
    0.21
    alone
    0.21
     anymore
    0.20
    __;
    0.20
     alone
    0.19
     Äijâu
    0.18
    Act Density 0.264%

    No Known Activations