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

    Neuronpedia

    INDEX
    Explanations

    references to the number "two"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.03
     Jefus
    -1.03
     itſelf
    -1.01
     himſelf
    -0.99
     themſelves
    -0.96
     Shakspeare
    -0.92
     Efq
    -0.90
    ſelf
    -0.89
     ſche
    -0.86
     ―――――
    -0.86
    POSITIVE LOGITS
     separate
    0.89
     very
    0.76
     distinct
    0.76
    separate
    0.75
     opposing
    0.72
     halves
    0.72
    thirds
    0.70
     contrasting
    0.69
     main
    0.69
     adjacent
    0.66
    Act Density 0.187%

    No Known Activations