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

    Neuronpedia

    INDEX
    Explanations

    phrases related to security and storage arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ì¼ĵ
    -0.17
    rosso
    -0.16
    mares
    -0.15
    akens
    -0.15
    ê¼
    -0.14
    /INFO
    -0.14
    abus
    -0.14
     tract
    -0.13
    autiful
    -0.13
    ousel
    -0.13
    POSITIVE LOGITS
     saf
    0.30
     vault
    0.28
     safe
    0.28
     lock
    0.26
     burg
    0.26
     burglary
    0.25
     Vaults
    0.25
     locks
    0.24
     locking
    0.23
     Safe
    0.23
    Act Density 0.012%

    No Known Activations