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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exploring different areas or fields

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving exploration or delving into various subjects or fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uid
    -0.70
    oppers
    -0.68
    âĤ¬
    -0.65
    die
    -0.64
    ĺħ
    -0.64
    rolley
    -0.63
    rising
    -0.61
    achy
    -0.60
     conveyed
    -0.60
    end
    -0.59
    POSITIVE LOGITS
     adulthood
    0.88
     unch
    0.80
    ricular
    0.75
     realms
    0.71
     infinity
    0.70
     Canaan
    0.68
     Wonderland
    0.67
     adolescence
    0.66
     fray
    0.65
    tnc
    0.64
    Act Density 0.059%

    No Known Activations