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

    Neuronpedia

    INDEX
    Explanations

    phrases or words that suggest a physical force or impact

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    awaru
    -0.68
     Palestin
    -0.67
    EMENT
    -0.67
    BILITY
    -0.67
     Democr
    -0.67
    TAIN
    -0.63
    GMT
    -0.61
     BDS
    -0.60
     VIDEOS
    -0.60
     Bethlehem
    -0.59
    POSITIVE LOGITS
    ashing
    1.19
    ogged
    1.17
    ojure
    1.17
    ipper
    1.14
    avier
    1.12
    amped
    1.10
    amps
    1.07
    umps
    1.06
    unky
    1.06
    ique
    1.04
    Act Density 0.009%

    No Known Activations