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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data access and systems vulnerability

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     !...
    -1.65
     ?...
    -1.64
     ftu
    -1.60
     fta
    -1.55
     effe
    -1.51
    :,,
    -1.50
     thut
    -1.50
     emphat
    -1.49
     purcha
    -1.49
     ftre
    -1.48
    POSITIVE LOGITS
     both
    0.85
     the
    0.77
     each
    0.76
     those
    0.75
     our
    0.73
     their
    0.73
     every
    0.71
     whatever
    0.70
     what
    0.68
     these
    0.67
    Act Density 0.726%

    No Known Activations