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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hobbies and interests

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Dialog
    -0.68
    struct
    -0.64
    Prosecut
    -0.62
    Delivery
    -0.61
     administr
    -0.60
     arrang
    -0.59
     administration
    -0.59
    Islamic
    -0.58
    ictional
    -0.57
     Officers
    -0.57
    POSITIVE LOGITS
     rejoice
    1.82
     beware
    1.59
     alike
    1.35
     flock
    1.11
     cringe
    0.97
     Beware
    0.97
     rave
    0.96
     appreciate
    0.93
     crave
    0.91
     everywhere
    0.90
    Act Density 0.197%

    No Known Activations