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

    Neuronpedia

    INDEX
    Explanations

    phrases related to requests or criticisms for action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate calls or requests for action from various parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.77
    puter
    -0.73
    cum
    -0.72
    imate
    -0.71
    pleted
    -0.71
    isode
    -0.70
    edited
    -0.70
    iven
    -0.69
    mix
    -0.69
    rils
    -0.68
    POSITIVE LOGITS
     afar
    1.46
     abroad
    1.20
     within
    1.01
     constituents
    0.99
     inside
    0.97
     passers
    0.96
     strangers
    0.90
     listeners
    0.88
     outsiders
    0.88
     outside
    0.86
    Act Density 0.141%

    No Known Activations