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

    Neuronpedia

    INDEX
    Explanations

    casual second-person plural pronouns and references to a group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lope
    -0.17
    423
    -0.16
    ifer
    -0.16
     himself
    -0.16
    ini
    -0.15
     indeed
    -0.14
    cente
    -0.14
    irl
    -0.14
     itself
    -0.14
     Himself
    -0.14
    POSITIVE LOGITS
    dio
    0.16
    äºķ
    0.15
    ·
    0.15
    arkin
    0.15
    Assignable
    0.15
     Ages
    0.14
    412
    0.14
    /MIT
    0.14
    VERR
    0.14
     limp
    0.14
    Act Density 0.034%

    No Known Activations