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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is extraordinary or unprecedented

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating unprecedented experiences or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ
    -0.66
    Staff
    -0.64
    Administ
    -0.63
    ·
    -0.62
    area
    -0.62
    BAT
    -0.62
    Michelle
    -0.62
    irrel
    -0.62
    abet
    -0.62
    oret
    -0.61
    POSITIVE LOGITS
     existed
    0.73
     tasted
    0.73
     realised
    0.73
     anecd
    0.71
    ankind
    0.71
     apologized
    0.70
     realizing
    0.70
    heed
    0.69
     encountering
    0.67
     seen
    0.66
    Act Density 0.029%

    No Known Activations