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

    Neuronpedia

    INDEX
    Explanations

    sequences of newline characters, spaces, and certain punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ookie
    -0.17
    _DEPRECATED
    -0.15
    oke
    -0.15
    oa
    -0.14
    lore
    -0.13
    odes
    -0.13
    åij
    -0.13
     Survivor
    -0.13
    ossier
    -0.13
    yun
    -0.13
    POSITIVE LOGITS
    lette
    0.16
    ÃŃst
    0.16
    gran
    0.15
    LETTE
    0.15
    reek
    0.15
     gran
    0.14
    Ĵ
    0.14
    AccessType
    0.14
    kur
    0.13
    atoria
    0.13
    Act Density 0.020%

    No Known Activations