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

    Neuronpedia

    INDEX
    Explanations

    references to positive or negative reception and success

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "bo" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dedication
    -0.60
    ware
    -0.60
    CLASSIFIED
    -0.58
    theless
    -0.58
     Millennium
    -0.58
     à¨
    -0.56
    nexus
    -0.56
     neutrality
    -0.55
     Sons
    -0.55
     specificity
    -0.55
    POSITIVE LOGITS
    gey
    1.30
    oby
    1.25
    ogie
    1.19
    oms
    1.15
    quet
    1.05
    zos
    1.02
    omer
    1.01
    zo
    1.00
    ogi
    0.99
    ister
    0.99
    Act Density 0.023%

    No Known Activations