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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and physical contact between individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ratom
    -0.65
    cheat
    -0.63
     gravy
    -0.60
     Bots
    -0.58
    jun
    -0.58
    angular
    -0.57
     Ging
    -0.57
     Mueller
    -0.57
     Auburn
    -0.56
    Ps
    -0.56
    POSITIVE LOGITS
    enment
    0.70
     withd
    0.69
     arrang
    0.68
    holm
    0.67
    amorph
    0.66
    iosis
    0.65
    Station
    0.62
    inian
    0.62
    ________________________________________________________________
    0.61
    ibility
    0.61
    Act Density 6.986%

    No Known Activations