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

    Neuronpedia

    INDEX
    Explanations

    references to professional roles and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    implify
    -0.15
    ë§IJ
    -0.14
    eka
    -0.14
    erse
    -0.14
    aco
    -0.14
     Ler
    -0.14
    oine
    -0.13
    leine
    -0.13
     konkrét
    -0.13
    editable
    -0.13
    POSITIVE LOGITS
    LING
    0.14
    oulouse
    0.14
    TestCase
    0.14
    rupt
    0.14
     Approved
    0.14
    abis
    0.14
     Ramp
    0.14
    ryption
    0.14
    /of
    0.13
    gress
    0.13
    Act Density 0.047%

    No Known Activations