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

    Neuronpedia

    INDEX
    Explanations

    terms indicating ease or simplicity

    oai_token-act-pair · gpt-3.5-turbo

    the adverb "easily" and its variations, indicating simplicity or accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grave
    -0.77
    geist
    -0.74
    iery
    -0.71
    mut
    -0.69
    raints
    -0.68
    ornia
    -0.68
    oft
    -0.65
    elson
    -0.64
    soc
    -0.63
    reon
    -0.63
    POSITIVE LOGITS
    Jet
    1.01
     identifiable
    0.84
     readable
    0.82
    jet
    0.80
     accessible
    0.80
     adv
    0.73
     attain
    0.72
     accommod
    0.72
     prey
    0.71
    ect
    0.71
    Act Density 0.019%

    No Known Activations