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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific technical process or chemical reaction

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersive
    -0.91
    icum
    -0.88
    arious
    -0.84
    acies
    -0.80
    undy
    -0.79
    enegger
    -0.78
    ersen
    -0.77
    nesday
    -0.74
    romeda
    -0.74
    ancial
    -0.70
    POSITIVE LOGITS
    xual
    1.94
    ño
    0.98
    lled
    0.90
    lly
    0.89
     inhibitors
    0.88
    hift
    0.86
    ñ
    0.85
    lling
    0.82
     inhibitor
    0.79
    cond
    0.75
    Act Density 0.028%

    No Known Activations