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

    Neuronpedia

    INDEX
    Explanations

    references to significant actions and positions related to social issues and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.61
     destro
    -0.58
     Vaugh
    -0.57
     assum
    -0.55
     withd
    -0.55
     thous
    -0.53
     cryst
    -0.52
     [*
    -0.51
     tradem
    -0.51
     proble
    -0.51
    POSITIVE LOGITS
    cigarettes
    0.54
    ratom
    0.48
     Belfast
    0.47
    cigarette
    0.46
    rock
    0.46
    hra
    0.45
    aus
    0.45
    wolves
    0.44
    hillary
    0.43
     Corbyn
    0.43
    Act Density 1.155%

    No Known Activations