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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    uncertainty and ambiguous situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endorsements
    -0.75
     adherents
    -0.73
     communities
    -0.73
     proponents
    -0.71
     grassroots
    -0.70
     internationally
    -0.69
     franchises
    -0.69
     advocates
    -0.68
    rists
    -0.68
     endors
    -0.67
    POSITIVE LOGITS
     downstairs
    1.00
     yesterday
    0.99
     haha
    0.97
     earlier
    0.88
    Yesterday
    0.85
     :(
    0.84
     asleep
    0.81
     upstairs
    0.79
     potion
    0.78
     beforehand
    0.75
    Act Density 0.952%

    No Known Activations