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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating consequences or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causal relationship outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lineback
    -0.70
     butterflies
    -0.70
     Brewers
    -0.67
     spots
    -0.66
     roofs
    -0.65
     Mariners
    -0.63
     Majesty
    -0.61
    ockets
    -0.60
    tera
    -0.60
     captains
    -0.60
    POSITIVE LOGITS
    ainer
    0.79
    uary
    0.76
     thereof
    0.76
    DragonMagazine
    0.75
    ulator
    0.72
    gha
    0.71
    ãĥĥãĥī
    0.71
    uration
    0.70
    ivity
    0.69
    Reviewer
    0.69
    Act Density 0.017%

    No Known Activations