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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal and workplace issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    e
    -0.98
     J
    -0.95
     T
    -0.94
     S
    -0.93
     h
    -0.93
    aarrggbb
    -0.92
     E
    -0.91
    E
    -0.90
     K
    -0.90
     O
    -0.89
    POSITIVE LOGITS
     myſelf
    1.55
     themſelves
    1.53
     viſ
    1.48
     Theſe
    1.44
     faſt
    1.44
     pleaſure
    1.43
    ſelves
    1.40
     deſt
    1.39
     itſelf
    1.38
     Diſ
    1.37
    Act Density 0.550%

    No Known Activations