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

    Neuronpedia

    INDEX
    Explanations

    technical terms and product names

    oai_token-act-pair · gpt-3.5-turbo

    specific technical specifications and model identifiers related to devices and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.81
    adem
    -0.81
    tu
    -0.77
    robe
    -0.76
    comed
    -0.76
    marg
    -0.73
    mat
    -0.73
    arial
    -0.73
    racial
    -0.71
    natureconservancy
    -0.70
    POSITIVE LOGITS
     XV
    0.84
     XI
    0.82
     VII
    0.82
     XIV
    0.81
     III
    0.81
     Plus
    0.79
     XVI
    0.77
     XII
    0.74
     II
    0.73
     VIII
    0.69
    Act Density 0.202%

    No Known Activations