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

    Neuronpedia

    INDEX
    Explanations

    phrases related to easy accessibility and manipulation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "easily"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iery
    -0.74
    geist
    -0.74
    grave
    -0.72
    reon
    -0.72
    rum
    -0.71
    mut
    -0.71
    inburgh
    -0.66
    raints
    -0.65
    elson
    -0.64
    oft
    -0.63
    POSITIVE LOGITS
    Jet
    1.05
     accessible
    0.82
    jet
    0.81
     identifiable
    0.80
     readable
    0.77
     accommod
    0.75
     understandable
    0.75
     achievable
    0.72
     prey
    0.72
     attain
    0.71
    Act Density 0.016%

    No Known Activations