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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns 'I' in sentences

    oai_token-act-pair · gpt-3.5-turbo

    first-person singular pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imum
    -0.61
     Cost
    -0.61
    redients
    -0.59
    tains
    -0.59
     PTS
    -0.59
     Impact
    -0.57
     excess
    -0.57
    artney
    -0.57
    tnc
    -0.56
     density
    -0.56
    POSITIVE LOGITS
    'm
    1.56
    've
    1.38
    'll
    1.21
     suppose
    1.20
    'd
    1.14
     am
    1.08
     presume
    1.07
     guess
    1.07
     dunno
    1.02
    RL
    0.98
    Act Density 0.318%

    No Known Activations