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

    Neuronpedia

    INDEX
    Explanations

    terms indicative of clarity or certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to clarity and coherence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hops
    -1.13
    aunts
    -0.91
    lees
    -0.87
    hots
    -0.85
    events
    -0.83
    ifles
    -0.80
     balloons
    -0.79
    rants
    -0.79
    packages
    -0.79
    ummies
    -0.77
    POSITIVE LOGITS
     solution
    1.06
     explanation
    1.01
     approximation
    0.98
     indication
    0.97
     antidote
    0.95
     amount
    0.94
     contender
    0.93
     presence
    0.93
     slate
    0.89
     relationship
    0.89
    Act Density 0.253%

    No Known Activations