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

    Neuronpedia

    INDEX
    Explanations

    situations involving personal relationships and emotional experiences

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

    after the word "I" or pronouns

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThemeOverlay
    -0.73
     fince
    -0.70
     Inscrivez
    -0.70
     Theſe
    -0.68
     Савезне
    -0.68
     Monfieur
    -0.67
    Portail
    -0.65
     Majefty
    -0.64
     Chriftian
    -0.64
    脚注の使い方
    -0.62
    POSITIVE LOGITS
     immediately
    1.00
    immediately
    0.84
    まず
    0.79
    Immediately
    0.78
     Immediately
    0.77
     automatically
    0.77
     first
    0.72
     inmediatamente
    0.71
    必ず
    0.71
     instantly
    0.71
    Act Density 0.433%

    No Known Activations