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

    Neuronpedia

    INDEX
    Explanations

    phrases describing something as extreme or significant

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or negativity related to situations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apons
    -0.78
    gemony
    -0.77
    alks
    -0.75
    eton
    -0.74
    everal
    -0.72
    abases
    -0.72
    illions
    -0.70
    undreds
    -0.69
    earances
    -0.68
    awaru
    -0.67
    POSITIVE LOGITS
     nightmare
    0.98
     predictor
    0.98
     rarity
    0.97
     fixture
    0.96
    starter
    0.95
     nuisance
    0.95
     staple
    0.93
     annoyance
    0.91
     understatement
    0.89
     headache
    0.88
    Act Density 0.296%

    No Known Activations