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

    Neuronpedia

    INDEX
    Explanations

    discussions related to crime and harm perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bias
    -0.16
     evolution
    -0.15
    rei
    -0.15
    Bias
    -0.14
     tribal
    -0.14
     man
    -0.14
     bias
    -0.14
     Tribal
    -0.14
     Ecc
    -0.14
     Evolution
    -0.13
    POSITIVE LOGITS
     disc
    0.22
     Fou
    0.19
     neoliberal
    0.18
     Contest
    0.18
    spaces
    0.18
     spaces
    0.18
    valor
    0.17
     Scalar
    0.17
     meanings
    0.17
     spatial
    0.17
    Act Density 0.384%

    No Known Activations