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

    Neuronpedia

    INDEX
    Explanations

    phrases related to politics and global events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.78
    buster
    -0.66
    breaker
    -0.64
    percent
    -0.62
    intend
    -0.61
    ALLY
    -0.60
     relayed
    -0.60
     Refer
    -0.60
    Refer
    -0.60
     exponent
    -0.59
    POSITIVE LOGITS
     undone
    1.02
    overs
    0.93
     scars
    0.92
     behind
    0.88
     unanswered
    0.84
     unexpl
    0.83
     him
    0.80
     gaping
    0.79
     footprints
    0.78
     intact
    0.78
    Act Density 0.031%

    No Known Activations