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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases indicating future or temporal proximity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to timeframes or periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apego
    -0.65
    paio
    -0.62
    Reviewer
    -0.62
     verbs
    -0.59
     labels
    -0.58
    Tags
    -0.58
    Obs
    -0.57
     passwords
    -0.57
     chained
    -0.56
     Chaser
    -0.55
    POSITIVE LOGITS
     vicinity
    0.95
    ixties
    0.94
     midst
    0.91
     vein
    0.90
     guise
    0.89
     context
    0.80
     nutshell
    0.78
     aftermath
    0.76
     sense
    0.76
     realm
    0.75
    Act Density 0.332%

    No Known Activations