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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connectors in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.89
    ſelf
    -0.87
     itſelf
    -0.87
     purpoſe
    -0.83
     themſelves
    -0.83
    хьтан
    -0.82
     pleaſure
    -0.81
     Majefty
    -0.80
     Theſe
    -0.80
     Jefus
    -0.80
    POSITIVE LOGITS
    etc
    0.69
    Etc
    0.65
     etc
    0.58
    цездатний
    0.57
     Etc
    0.54
     also
    0.51
    /
    0.51
     anche
    0.51
    And
    0.50
    ogia
    0.49
    Act Density 0.185%

    No Known Activations