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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the passage of time or progression of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing hopefulness or concern about the future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    initely
    -0.65
     specialize
    -0.60
     intrigued
    -0.60
     aliases
    -0.60
     curious
    -0.60
     stances
    -0.60
     ALWAYS
    -0.56
     rarely
    -0.56
     doubtless
    -0.55
     questionnaire
    -0.55
    POSITIVE LOGITS
     anymore
    1.05
    peat
    0.82
     anytime
    0.79
     nor
    0.78
    enough
    0.74
     bloodshed
    0.70
    acea
    0.69
     any
    0.69
    warts
    0.68
     fruition
    0.67
    Act Density 0.742%

    No Known Activations