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

    Neuronpedia

    INDEX
    Explanations

    symbols or punctuation marks that indicate special formatting or notes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows greetings or salutations

    np_acts-logits-general · gemini-2.0-flash

    career, following, livelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     furthermore
    -0.86
     moreover
    -0.86
     entanto
    -0.85
    Ayrıca
    -0.80
    omiast
    -0.78
     ayrıca
    -0.77
    however
    -0.76
     however
    -0.74
    Etc
    -0.73
     außerdem
    -0.73
    POSITIVE LOGITS
    When
    0.97
     When
    0.89
    Dear
    0.88
    Welcome
    0.85
    Hello
    0.84
     Hello
    0.79
     Welcome
    0.79
    Today
    0.77
     Greetings
    0.76
    Greetings
    0.75
    Act Density 0.574%

    No Known Activations