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

    Neuronpedia

    INDEX
    Explanations

    first person plural pronouns

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or collective experience and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cade
    -0.63
    uy
    -0.63
    bender
    -0.63
    Correct
    -0.62
    ieu
    -0.60
     extant
    -0.60
    IOR
    -0.60
    20439
    -0.59
     remaining
    -0.58
    acci
    -0.58
    POSITIVE LOGITS
    're
    0.88
    'll
    0.85
     ain
    0.84
    've
    0.80
     wanna
    0.71
    'm
    0.66
     don
    0.65
     âĢ¦"
    0.64
    asso
    0.64
    rises
    0.64
    Act Density 0.274%

    No Known Activations