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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regulations and new policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     congr
    -0.15
    adera
    -0.15
    verse
    -0.14
    ESSAGES
    -0.14
    entes
    -0.14
    ril
    -0.14
    727
    -0.14
    woods
    -0.13
    quirer
    -0.13
     latter
    -0.13
    POSITIVE LOGITS
    /new
    0.21
    ,new
    0.18
     recruits
    0.17
    sworth
    0.16
    bish
    0.15
     Zealand
    0.15
    -wave
    0.15
    acct
    0.14
    ington
    0.14
     WaitForSeconds
    0.14
    Act Density 0.412%

    No Known Activations