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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols used in equations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.59
     ban
    -0.54
     
    -0.53
     N
    -0.51
     por
    -0.50
     a
    -0.49
     n
    -0.49
     dual
    -0.48
     P
    -0.47
     (
    -0.47
    POSITIVE LOGITS
    
    1.33
     Efq
    1.27
     Monfieur
    1.26
     pleaſure
    1.21
    ſelf
    1.21
    ſelves
    1.20
     purpoſe
    1.19
     Majefty
    1.19
     Theſe
    1.18
     Anſ
    1.17
    Act Density 0.948%

    No Known Activations