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

    Neuronpedia

    INDEX
    Explanations

    instances of specific single letter words or abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antly
    -0.13
    decess
    -0.13
    ój
    -0.13
    ersiz
    -0.12
    loat
    -0.12
    λοι
    -0.12
     célib
    -0.12
    seudo
    -0.12
    Ä°S
    -0.12
    onymous
    -0.12
    POSITIVE LOGITS
    malink
    0.15
    urum
    0.15
    ↵
    0.14
    aes
    0.14
    oooooooo
    0.14
    odore
    0.13
    aal
    0.13
    etheless
    0.13
    utut
    0.13
    :\
    0.13
    Act Density 0.385%

    No Known Activations