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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a sense of understanding or perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consort
    -0.16
    ãĥ¥ãĥ¼
    -0.15
    hung
    -0.15
    ÑĢава
    -0.14
    count
    -0.14
    Lon
    -0.14
    perse
    -0.14
    lon
    -0.14
    oga
    -0.14
     counted
    -0.14
    POSITIVE LOGITS
    illes
    0.15
    ahat
    0.15
     accomplishment
    0.15
    liness
    0.14
    ÅĻej
    0.14
    oss
    0.14
     relief
    0.14
    cape
    0.14
     urgency
    0.14
     Ent
    0.13
    Act Density 0.022%

    No Known Activations