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

    Neuronpedia

    INDEX
    Explanations

    references to marsh-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to marshals and marshmallow-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.81
    aughs
    -0.68
     tense
    -0.64
     deaf
    -0.64
     Belt
    -0.61
    OPLE
    -0.60
     WikiLeaks
    -0.59
     superficial
    -0.58
     human
    -0.58
     Fairfax
    -0.58
    POSITIVE LOGITS
    mallow
    1.64
     marsh
    1.32
    alled
    1.09
    alling
    1.02
    aling
    1.02
    aled
    0.99
     Marshal
    0.97
    ãĤ©
    0.94
    als
    0.93
    Marsh
    0.88
    Act Density 0.005%

    No Known Activations