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

    Neuronpedia

    INDEX
    Explanations

    references to various roles or positions that individuals hold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lingen
    -0.17
    nga
    -0.15
    enstein
    -0.14
     Hoff
    -0.14
    ards
    -0.14
     brothers
    -0.14
    udder
    -0.14
    ian
    -0.14
     ab
    -0.14
     Getter
    -0.14
    POSITIVE LOGITS
    urray
    0.15
    927
    0.15
    lessly
    0.15
    åŃ
    0.15
    roj
    0.14
    Concrete
    0.14
     PAC
    0.14
    azen
    0.14
    ihan
    0.14
     roll
    0.14
    Act Density 0.017%

    No Known Activations