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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating formal or legal disclaimers and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.14
    frau
    -0.14
    evin
    -0.14
    459
    -0.14
     Invocation
    -0.13
    zon
    -0.13
    emma
    -0.13
    ITU
    -0.13
    ebra
    -0.13
    æĵį
    -0.13
    POSITIVE LOGITS
    -the
    0.29
    _the
    0.25
    -The
    0.22
    thew
    0.20
    ãĤ¶
    0.19
    the
    0.19
    ithe
    0.18
     THE
    0.17
    The
    0.17
    .the
    0.17
    Act Density 0.699%

    No Known Activations