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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal relationships, particularly involving boyfriends and girlfriends

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.83
    Interstitial
    -0.79
     Printed
    -0.78
     Parables
    -0.73
    kefeller
    -0.70
    TPPStreamerBot
    -0.68
    gard
    -0.68
    interstitial
    -0.68
     cones
    -0.65
    urgical
    -0.64
    POSITIVE LOGITS
     girlfriend
    0.99
     boyfriend
    0.92
     whom
    0.86
    girlfriend
    0.86
     Romeo
    0.84
     partner
    0.81
    friend
    0.80
    hetical
    0.80
     Erica
    0.76
     Vanessa
    0.75
    Act Density 0.038%

    No Known Activations