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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal pronouns and possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.46
     Casting
    -0.45
     Unlimited
    -0.45
    assembly
    -0.43
     Noon
    -0.43
     Jindal
    -0.43
    math
    -0.42
     Gerard
    -0.41
     Siege
    -0.40
     Around
    -0.40
    POSITIVE LOGITS
    'll
    0.78
    'd
    0.72
    've
    0.72
     own
    0.71
    're
    0.63
     conduc
    0.63
     reluct
    0.62
    self
    0.59
     encount
    0.59
    zbollah
    0.59
    Act Density 1.055%

    No Known Activations