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

    Neuronpedia

    INDEX
    Explanations

    references to incidents of racism and hate crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rebel
    -0.17
     rebels
    -0.17
     Rebellion
    -0.16
     Rebels
    -0.15
     rebell
    -0.15
     rebellion
    -0.15
    sey
    -0.14
    ronic
    -0.14
    ako
    -0.14
    irez
    -0.14
    POSITIVE LOGITS
     hate
    0.44
     Hate
    0.39
     hatred
    0.32
    _hat
    0.30
     hates
    0.30
     hateful
    0.29
    hat
    0.29
    Hat
    0.28
     Hat
    0.28
     hat
    0.28
    Act Density 0.185%

    No Known Activations