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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental processes and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.67
     ſeine
    -0.65
    <unused43>
    -0.65
    <unused42>
    -0.65
    <unused41>
    -0.65
    <pad>
    -0.65
    <unused28>
    -0.64
     deſſen
    -0.64
    <unused16>
    -0.64
    <unused17>
    -0.64
    POSITIVE LOGITS
     مك
    0.35
     zero
    0.34
     gal
    0.33
    ToReturn
    0.33
     bat
    0.32
     co
    0.31
     المك
    0.30
     :
    0.30
    vendor
    0.30
     ch
    0.29
    Act Density 0.048%

    No Known Activations