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

    Neuronpedia

    INDEX
    Explanations

    phrases related to secrecy or classified information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccione
    -0.15
    един
    -0.14
    �t
    -0.14
    å°Ĭ
    -0.14
    �
    -0.14
     Bab
    -0.14
    ysz
    -0.13
     subscription
    -0.13
     Prince
    -0.13
    /***************************************************************************↵
    -0.13
    POSITIVE LOGITS
     SCP
    0.40
    SCP
    0.40
     Foundation
    0.35
     scp
    0.29
    Foundation
    0.27
    foundation
    0.26
     foundation
    0.26
    âĸĪâĸĪ
    0.25
    scp
    0.24
     containment
    0.24
    Act Density 0.004%

    No Known Activations