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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    pronouns in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Helm
    -0.77
    Newsletter
    -0.66
     Peak
    -0.65
     Option
    -0.61
    Enlarge
    -0.60
     Outside
    -0.59
     Junk
    -0.59
     Lump
    -0.59
     Ammunition
    -0.59
     Mob
    -0.58
    POSITIVE LOGITS
    chy
    0.92
    cause
    0.87
    'll
    0.84
    self
    0.83
    tis
    0.80
    TPPStreamerBot
    0.79
    just
    0.79
    ÃĥÃĤ
    0.79
    arers
    0.78
    pecially
    0.78
    Act Density 0.209%

    No Known Activations