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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recommendations and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agen
    -0.15
     Gors
    -0.15
    .Must
    -0.14
    enin
    -0.14
    åĩĿ
    -0.13
    æĪ¸
    -0.13
    aby
    -0.13
    /epl
    -0.13
    inos
    -0.13
    itten
    -0.13
    POSITIVE LOGITS
    ushman
    0.15
    etur
    0.15
    erguson
    0.15
    etter
    0.15
    izoph
    0.14
     Eig
    0.14
    626
    0.14
    ditor
    0.14
     way
    0.14
    seg
    0.14
    Act Density 0.196%

    No Known Activations