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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ease or simplicity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    grave
    -0.87
    eters
    -0.86
    hips
    -0.80
    emp
    -0.73
    orp
    -0.73
    yss
    -0.72
    raints
    -0.71
    shall
    -0.70
    reon
    -0.68
    inburgh
    -0.68
    POSITIVE LOGITS
    Jet
    1.00
     prey
    0.89
    going
    0.80
     forgiving
    0.77
     understandable
    0.76
     easy
    0.73
     accessible
    0.72
     stroll
    0.71
     achievable
    0.70
    Reply
    0.70
    Act Density 0.653%

    No Known Activations