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

    Neuronpedia

    INDEX
    Explanations

    significant numeric data and its contextual relevance in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.73
     kaarangay
    -0.68
    tvguidetime
    -0.64
    verwijspagina
    -0.63
    <unused23>
    -0.61
    <unused14>
    -0.61
    <unused41>
    -0.60
    <unused43>
    -0.60
    <unused28>
    -0.60
    <unused8>
    -0.60
    POSITIVE LOGITS
    SourceChecksum
    0.35
    num
    0.32
     quarante
    0.30
    most
    0.30
    それでは
    0.29
    wo
    0.29
     secondaires
    0.28
    オ
    0.28
     written
    0.27
    stor
    0.27
    Act Density 0.084%

    No Known Activations