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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by contractions

    oai_token-act-pair · gpt-3.5-turbo

    references to the speaker's perspective or personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PTS
    -0.67
    tains
    -0.60
     totality
    -0.58
     Plaint
    -0.58
     outing
    -0.57
    Ħ¢
    -0.56
    Individual
    -0.56
     extant
    -0.55
     footwear
    -0.55
     relevance
    -0.54
    POSITIVE LOGITS
    'm
    1.63
     dunno
    1.35
    've
    1.27
    'll
    1.26
     suppose
    1.24
     swear
    1.20
     wanna
    1.19
     guess
    1.18
     gotta
    1.14
     am
    1.07
    Act Density 0.207%

    No Known Activations