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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to a structured process or result

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.97
     himſelf
    -0.88
    клопе
    -0.80
     Monfieur
    -0.78
     becauſe
    -0.77
     uſed
    -0.74
    EndContext
    -0.74
     alſo
    -0.74
     myſelf
    -0.73
     juſt
    -0.73
    POSITIVE LOGITS
     оригіналу
    0.59
    ,
    0.50
     —
    0.49
    ReusableCell
    0.47
    —
    0.45
    planet
    0.45
     Planet
    0.45
     Drittan
    0.44
    communities
    0.43
    .
    0.42
    Act Density 0.042%

    No Known Activations