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

    Neuronpedia

    INDEX
    Explanations

    references to authorship or attribution in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tome
    -0.16
    andro
    -0.15
    mys
    -0.14
    prox
    -0.14
    Ìĥ
    -0.14
    quential
    -0.14
    夫人
    -0.14
    andas
    -0.14
    696
    -0.14
     Stanton
    -0.14
    POSITIVE LOGITS
     reporter
    0.22
     reporters
    0.21
    	Il
    0.18
     bureau
    0.17
     staff
    0.17
     bure
    0.17
    ureau
    0.17
     correspondent
    0.16
     Associated
    0.16
    Reporter
    0.16
    Act Density 0.048%

    No Known Activations