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

    Neuronpedia

    INDEX
    Explanations

    instances of apostrophes used in contractions or possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kili
    -0.16
    hiba
    -0.15
    'hui
    -0.15
    æĽľ
    -0.15
    (åľŁ
    -0.14
    InstanceState
    -0.14
    ocale
    -0.14
    ATEST
    -0.14
    Violation
    -0.14
    ТÐŀ
    -0.14
    POSITIVE LOGITS
    um
    0.21
    em
    0.20
    cept
    0.19
    uns
    0.18
    er
    0.17
    cm
    0.17
    til
    0.16
    neath
    0.16
    UM
    0.16
    im
    0.16
    Act Density 0.012%

    No Known Activations