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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making decisions and taking action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aka
    -0.15
    apk
    -0.14
    iao
    -0.14
    .cum
    -0.14
     SITE
    -0.14
    ums
    -0.14
     elastic
    -0.14
    íŀ
    -0.14
    Eigen
    -0.14
    hind
    -0.14
    POSITIVE LOGITS
     mistake
    0.17
     mistakes
    0.16
     Lâm
    0.15
     arrang
    0.15
     decisions
    0.15
    utenberg
    0.15
     living
    0.14
    829
    0.14
    âĪł
    0.14
    660
    0.14
    Act Density 0.146%

    No Known Activations