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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consistency or conformity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "keeping."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OUN
    -0.70
    Merit
    -0.69
    Interstitial
    -0.69
    ones
    -0.65
    emphasis
    -0.63
    çīĪ
    -0.62
     Dud
    -0.62
    NetMessage
    -0.61
    swick
    -0.60
     Dism
    -0.60
    POSITIVE LOGITS
     tabs
    0.95
     keeping
    0.85
    keeping
    0.84
     vigil
    0.83
     track
    0.82
     pace
    0.81
     alive
    0.71
     afloat
    0.71
     preserving
    0.70
     rall
    0.69
    Act Density 0.010%

    No Known Activations