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

    Neuronpedia

    INDEX
    Explanations

    titles and roles associated with leadership or authority positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opal
    -0.15
    idth
    -0.15
    ãĥ¼ãĥĹ
    -0.15
    iolet
    -0.14
     goose
    -0.14
    iones
    -0.14
    .vs
    -0.14
    punk
    -0.14
    ayette
    -0.14
    ||(
    -0.13
    POSITIVE LOGITS
    nant
    0.16
    kaar
    0.14
    borg
    0.14
     subordinate
    0.14
     revolution
    0.14
    ynom
    0.14
     Rossi
    0.13
     unde
    0.13
    onet
    0.13
    iban
    0.13
    Act Density 0.234%

    No Known Activations