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

    Neuronpedia

    INDEX
    Explanations

    statements expressing opinions or beliefs with an emphasis on certainty

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases and expressions that indicate unfulfilled potential or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Weather
    -0.68
    Disk
    -0.67
    rouse
    -0.64
    Decl
    -0.64
    virt
    -0.62
     Ars
    -0.62
    sky
    -0.61
    Storm
    -0.59
     Sierra
    -0.57
     Background
    -0.57
    POSITIVE LOGITS
     gonna
    0.80
     ðŁij
    0.76
    âĺ
    0.71
    .''
    0.70
    ĵĺ
    0.70
    soDeliveryDate
    0.69
    ðŁij
    0.69
    selves
    0.67
     buddies
    0.67
    ĸļ
    0.66
    Act Density 0.135%

    No Known Activations