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

    Neuronpedia

    INDEX
    Explanations

    terms related to spatial or infrastructural changes and improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     T
    -1.06
     S
    -1.05
     J
    -1.03
     E
    -1.01
    E
    -0.99
     K
    -0.98
     P
    -0.96
     O
    -0.95
     G
    -0.95
     H
    -0.94
    POSITIVE LOGITS
     myſelf
    1.98
     themſelves
    1.93
     itſelf
    1.89
     Theſe
    1.81
     himſelf
    1.78
     Anſ
    1.75
    ſelves
    1.75
     ſever
    1.75
     pleaſure
    1.75
     Diſ
    1.71
    Act Density 0.646%

    No Known Activations