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

    Neuronpedia

    INDEX
    Explanations

    codes, numbers, and file names

    oai_token-act-pair · gpt-3.5-turbo

    numeric codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interf
    -0.81
    externalActionCode
    -0.80
     simplicity
    -0.70
     globalization
    -0.69
    annis
    -0.67
     reconc
    -0.66
    urally
    -0.66
     contrace
    -0.66
     slightest
    -0.64
     crossings
    -0.64
    POSITIVE LOGITS
     partName
    0.79
    orian
    0.74
    orians
    0.71
    df
    0.70
    ea
    0.68
    ae
    0.68
    },
    0.67
     Detention
    0.67
    >]
    0.67
    ensis
    0.66
    Act Density 0.069%

    No Known Activations