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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific interactions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     E
    -0.79
     M
    -0.74
     G
    -0.72
     C
    -0.72
     of
    -0.71
     B
    -0.70
     H
    -0.70
     N
    -0.70
     R
    -0.69
     P
    -0.68
    POSITIVE LOGITS
     Monfieur
    1.63
     myſelf
    1.51
     themſelves
    1.46
     Theſe
    1.35
    ſelf
    1.31
     himſelf
    1.30
     raiſ
    1.29
     becauſe
    1.28
     faſt
    1.26
     Shakspeare
    1.26
    Act Density 1.065%

    No Known Activations