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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical symbols and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gu
    -0.57
     combine
    -0.55
    antMatchers
    -0.53
    ...
    -0.50
     ε
    -0.50
     --
    -0.48
    rama
    -0.48
     gu
    -0.48
     pinulongan
    -0.48
     گذشته
    -0.47
    POSITIVE LOGITS
     itſelf
    0.93
     defaultstate
    0.83
     Monfieur
    0.81
     fathoms
    0.80
     myſelf
    0.80
     Cæsar
    0.80
     raiſ
    0.79
     GIPHY
    0.79
     dieß
    0.77
    kloped
    0.76
    Act Density 0.233%

    No Known Activations