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

    Neuronpedia

    INDEX
    Explanations

    first-person and third-person pronouns along with auxiliary verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expl
    -0.15
    ály
    -0.15
    ragen
    -0.15
     Gathering
    -0.14
    ordes
    -0.14
    azard
    -0.14
     çī
    -0.14
    547
    -0.14
    SizeMode
    -0.14
    arkin
    -0.14
    POSITIVE LOGITS
     witness
    0.21
    Witness
    0.20
     witnessing
    0.20
     witnesses
    0.20
     agreed
    0.19
     Witness
    0.19
     tac
    0.17
     clam
    0.15
    -talk
    0.15
    num
    0.15
    Act Density 0.035%

    No Known Activations