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

    Neuronpedia

    INDEX
    Explanations

    words related to power and influence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ´ãĤ¡
    -0.71
    pled
    -0.70
    nant
    -0.69
    itives
    -0.66
    xit
    -0.66
    esters
    -0.66
    ½
    -0.62
    ificantly
    -0.62
    ł
    -0.61
    NEY
    -0.61
    POSITIVE LOGITS
    izabeth
    1.24
    ibrary
    1.22
    usive
    1.11
    iquid
    1.07
    ixir
    1.04
    uded
    0.91
    uxe
    0.90
    uding
    0.86
    ipt
    0.86
    ijah
    0.85
    Act Density 0.040%

    No Known Activations