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

    Neuronpedia

    INDEX
    Explanations

    instances related to user logging activities and procedures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Blasio
    -0.73
    姫
    -0.68
    bite
    -0.65
    nesses
    -0.64
     Rub
    -0.59
    spr
    -0.59
    riages
    -0.59
     Boris
    -0.58
    cz
    -0.56
    silver
    -0.56
    POSITIVE LOGITS
     logs
    0.90
     logger
    0.84
     logging
    0.81
    istically
    0.77
    uid
    0.77
     login
    0.76
    onym
    0.74
     logged
    0.74
    login
    0.71
    iago
    0.70
    Act Density 8.511%

    No Known Activations