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

    Neuronpedia

    INDEX
    Explanations

    names of researchers or contributors associated with scientific publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.17
    ror
    -0.17
     Ipsum
    -0.15
    erty
    -0.14
    eson
    -0.14
    untu
    -0.14
    _DEFINITION
    -0.14
    лика
    -0.14
    orc
    -0.14
    éru
    -0.14
    POSITIVE LOGITS
     Morm
    0.16
    jab
    0.14
     Hoy
    0.14
    jas
    0.14
    asad
    0.14
     mos
    0.14
    lings
    0.14
    asing
    0.13
    istic
    0.13
    akers
    0.13
    Act Density 0.131%

    No Known Activations