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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating possession

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    },"
    -0.62
    vine
    -0.60
     Africa
    -0.60
     Wiki
    -0.60
     Newsweek
    -0.59
     Paste
    -0.58
     Goodman
    -0.58
     Pastebin
    -0.57
     HTTPS
    -0.56
    hap
    -0.56
    POSITIVE LOGITS
    sembly
    1.02
    */(
    0.91
    til
    0.81
    ©¶æ
    0.76
    ses
    0.75
    ctor
    0.74
    oting
    0.72
    cius
    0.71
    udes
    0.71
    Ĥİ
    0.70
    Act Density 0.280%

    No Known Activations