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

    Neuronpedia

    INDEX
    Explanations

    mentions of romantic partners, particularly girlfriends, and relationships within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "girlfriend" and its variations in relation to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.87
    Interstitial
    -0.74
    uchin
    -0.68
    ²¾
    -0.68
    TPPStreamerBot
    -0.68
    aus
    -0.67
    kefeller
    -0.66
    urgical
    -0.66
     centrif
    -0.65
    izen
    -0.64
    POSITIVE LOGITS
     girlfriend
    0.93
    girlfriend
    0.85
     boyfriend
    0.85
    hetical
    0.82
     whom
    0.81
     Romeo
    0.79
    gdala
    0.76
     Rachel
    0.72
     partner
    0.72
    ships
    0.71
    Act Density 0.038%

    No Known Activations