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

    Neuronpedia

    INDEX
    Explanations

    instances of first-person and third-person pronouns in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sublic
    -0.16
    ÑĥкÑĤ
    -0.14
     recru
    -0.14
    ÑĢоÑģÑĤо
    -0.13
     tavs
    -0.13
    ahun
    -0.13
     Majority
    -0.12
     istem
    -0.12
    enus
    -0.12
     Lund
    -0.12
    POSITIVE LOGITS
    gnore
    0.23
    bsite
    0.23
    apons
    0.21
    crease
    0.20
    ory
    0.17
    ward
    0.17
    ir
    0.17
    gether
    0.16
    i
    0.15
    icana
    0.15
    Act Density 0.089%

    No Known Activations