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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest a potential benefit or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating something leading to a specific outcome

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    soever
    -0.70
    phia
    -0.63
    alty
    -0.63
     underwent
    -0.62
     Steps
    -0.60
     Practices
    -0.58
    LY
    -0.57
     Sloan
    -0.56
     Notting
    -0.56
     Ples
    -0.56
    POSITIVE LOGITS
    geries
    0.90
    bidden
    0.76
    asty
    0.74
    imum
    0.67
    gery
    0.65
    culus
    0.65
    ê
    0.65
    izo
    0.65
    ument
    0.65
     easier
    0.65
    Act Density 0.051%

    No Known Activations