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

    Neuronpedia

    INDEX
    Explanations

    strong verbs related to emphasizing and highlighting

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    HOME
    -0.67
    avorite
    -0.66
     impulse
    -0.66
    TEXTURE
    -0.65
     negativity
    -0.63
     Solitaire
    -0.61
     vulnerability
    -0.61
    farm
    -0.61
     rubbish
    -0.61
    animate
    -0.60
    POSITIVE LOGITS
    ued
    1.22
    ighed
    1.17
    itled
    1.16
    uing
    1.11
    tained
    1.09
    uated
    1.08
    eled
    1.06
    ented
    1.06
    osed
    1.05
    icating
    1.05
    Act Density 0.179%

    No Known Activations