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

    references to possession or influence related to a group or individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.86
    adobe
    -0.76
    enhagen
    -0.74
     CrossRef
    -0.73
    Reviewed
    -0.73
    sson
    -0.71
    pection
    -0.71
    Timeout
    -0.71
    ucket
    -0.70
    igslist
    -0.68
    POSITIVE LOGITS
     own
    1.48
     agenda
    1.22
     interests
    1.20
     agendas
    1.20
     creations
    1.19
     desires
    1.19
     beliefs
    1.13
     wishes
    1.12
     delusions
    1.12
     ambitions
    1.09
    Act Density 0.237%

    No Known Activations