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

    Neuronpedia

    INDEX
    Explanations

    personal declarations or assertions made by the speaker

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "I" and its variations, indicating a focus on self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Awesome
    -0.75
    Multiple
    -0.70
    multiple
    -0.68
     CTR
    -0.67
    Intern
    -0.67
    Hey
    -0.65
    packs
    -0.65
    Looks
    -0.64
     Awesome
    -0.63
    Creat
    -0.62
    POSITIVE LOGITS
     confess
    1.11
     conclude
    1.10
     admire
    1.04
     conjecture
    1.03
     congratulate
    1.03
     presume
    1.02
     propose
    1.02
     rejoice
    1.01
     suppose
    1.01
     conceive
    1.00
    Act Density 0.200%

    No Known Activations