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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and possessive pronouns suggesting ownership

    oai_token-act-pair · gpt-3.5-turbo

    pronouns related to personal or collective identity and experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rig
    -0.71
    math
    -0.69
    cussion
    -0.67
     Cliff
    -0.66
    hess
    -0.64
     Remastered
    -0.63
     Dud
    -0.63
     Adv
    -0.62
     Voyager
    -0.61
     Ju
    -0.60
    POSITIVE LOGITS
     encount
    1.11
     encountered
    1.04
    've
    0.97
     deems
    0.94
     deem
    0.91
     learned
    0.87
     encounter
    0.85
     learnt
    0.84
     deemed
    0.83
     accumulated
    0.83
    Act Density 0.140%

    No Known Activations