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

    Neuronpedia

    INDEX
    Explanations

    references to political authority and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resumption
    -0.89
     rebirth
    -0.88
     Renewal
    -0.86
     renewal
    -0.86
     restarts
    -0.84
     retiring
    -0.83
     reopening
    -0.83
     restart
    -0.82
     restarting
    -0.82
     revival
    -0.82
    POSITIVE LOGITS
     undesirable
    0.62
     unsuitable
    0.60
     unhelpful
    0.59
     unacceptable
    0.54
     dangerous
    0.52
     dangereux
    0.52
     dangere
    0.51
     SqlDbType
    0.51
     unimportant
    0.51
     peligroso
    0.50
    Act Density 4.162%

    No Known Activations