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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social or political conflicts and tensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palest
    -0.66
     inval
    -0.66
     analysed
    -0.61
     calculating
    -0.58
     elig
    -0.58
     portraying
    -0.58
    aca
    -0.57
     describ
    -0.57
     secondly
    -0.57
     recommending
    -0.57
    POSITIVE LOGITS
    ptive
    0.74
    izens
    0.67
     project
    0.65
     drift
    0.62
    eatures
    0.61
    icular
    0.61
    ptions
    0.59
     sponge
    0.58
     counselor
    0.57
    OUS
    0.57
    Act Density 0.606%

    No Known Activations