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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and expressions of personal involvement or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansa
    -0.16
    iland
    -0.15
    509
    -0.15
    .libs
    -0.14
    adius
    -0.14
    omu
    -0.14
     sponsoring
    -0.13
    ny
    -0.13
    elper
    -0.13
    èĬĿ
    -0.13
    POSITIVE LOGITS
     personally
    0.20
     himself
    0.15
    embros
    0.15
    itm
    0.15
     Daly
    0.15
     FORCE
    0.15
    rog
    0.14
    FORCE
    0.14
    åĢij
    0.14
    sv
    0.14
    Act Density 0.143%

    No Known Activations