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

    Neuronpedia

    INDEX
    Explanations

    terms related to classification in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused74>
    -1.02
    <unused52>
    -1.02
    <unused41>
    -1.02
    <unused51>
    -1.02
    <unused14>
    -1.02
    <unused3>
    -1.02
    <unused16>
    -1.02
    <unused23>
    -1.02
    ementara
    -1.02
    <pad>
    -1.02
    POSITIVE LOGITS
     classification
    0.83
     Classification
    0.60
    classification
    0.58
    Classification
    0.51
     form
    0.51
    div
    0.50
    ↵
    0.48
     
    0.47
    liber
    0.47
    <eos>
    0.47
    Act Density 0.233%

    No Known Activations