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

    Neuronpedia

    INDEX
    Explanations

    references to political repression and human rights violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irm
    -0.17
    endas
    -0.16
    criptor
    -0.15
     Holocaust
    -0.15
     Iranian
    -0.14
     Iran
    -0.14
     Liber
    -0.14
    |i
    -0.14
    253
    -0.14
    æ´ĭ
    -0.14
    POSITIVE LOGITS
     Che
    0.32
     Ing
    0.31
    Ing
    0.25
     Gro
    0.25
    Che
    0.23
     che
    0.22
    _che
    0.20
     ing
    0.19
    -che
    0.19
     Caucas
    0.18
    Act Density 0.028%

    No Known Activations