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

    Neuronpedia

    INDEX
    Explanations

    words related to intermittent events or situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to challenges and uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shroud
    -0.72
     shift
    -0.67
    ĺħ
    -0.66
     Improvement
    -0.65
     Oaks
    -0.65
     Messenger
    -0.64
     prisoner
    -0.64
     Declaration
    -0.63
     Butterfly
    -0.63
     House
    -0.62
    POSITIVE LOGITS
    ency
    1.49
    abilities
    1.34
    encies
    1.34
    ably
    1.31
    ents
    1.29
    ently
    1.27
    ancies
    1.26
    ational
    1.26
    ential
    1.22
    atell
    1.20
    Act Density 0.081%

    No Known Activations