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

    Neuronpedia

    INDEX
    Explanations

    phrases involving criticism or pressure from various sources

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sources of criticism or pressure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    puter
    -0.82
    imate
    -0.74
    pleted
    -0.72
    iven
    -0.70
    gru
    -0.70
    nex
    -0.70
    film
    -0.69
    é¾įåĸļ士
    -0.68
    merce
    -0.68
    nets
    -0.68
    POSITIVE LOGITS
     afar
    1.41
     abroad
    1.10
     passers
    0.98
     constituents
    0.97
     inside
    0.89
     within
    0.87
     listeners
    0.85
     creditors
    0.84
     superiors
    0.83
     commenters
    0.83
    Act Density 0.105%

    No Known Activations