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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the perception of support or discontent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agate
    -0.84
    ramids
    -0.73
    ocr
    -0.71
    FORMATION
    -0.68
    querque
    -0.68
     Accessed
    -0.67
    verage
    -0.66
     totaling
    -0.62
    record
    -0.62
    killing
    -0.62
    POSITIVE LOGITS
     onlook
    0.99
     observers
    0.96
     economists
    0.94
     commenters
    0.94
     reviewers
    0.92
     physicists
    0.92
     pundits
    0.89
     commentators
    0.88
     Krugman
    0.88
     locals
    0.88
    Act Density 0.160%

    No Known Activations