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

    Neuronpedia

    INDEX
    Explanations

    sentences related to education and learning

    oai_token-act-pair · gpt-3.5-turbo

    references to education or educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favour
    -0.73
     thor
    -0.64
    ãĥ£
    -0.62
     Unloaded
    -0.62
     scissors
    -0.62
     Whitman
    -0.61
    sand
    -0.60
    gey
    -0.60
     mirrors
    -0.59
    Īè
    -0.59
    POSITIVE LOGITS
    owship
    0.92
    lishes
    0.91
    ngth
    0.79
     Lauder
    0.79
    uve
    0.78
    rete
    0.71
    lement
    0.71
    ateg
    0.70
     Pradesh
    0.70
    ement
    0.70
    Act Density 0.189%

    No Known Activations