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

    Neuronpedia

    INDEX
    Explanations

    instances where someone intervenes or takes action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    MAT
    -0.70
    omnia
    -0.63
    unct
    -0.63
    MQ
    -0.61
     proceeds
    -0.60
    iter
    -0.59
     Vend
    -0.58
    tumblr
    -0.58
    summary
    -0.57
    UFF
    -0.57
    POSITIVE LOGITS
     fray
    0.81
    circle
    0.80
     Desk
    0.72
     decisively
    0.70
     cautiously
    0.70
     boldly
    0.69
    elight
    0.69
    adra
    0.67
    lit
    0.67
     forefront
    0.67
    Act Density 0.038%

    No Known Activations