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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and emotional responses directed towards individuals

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

    Second-person pronouns, often misspelled

    np_acts-logits-general · gemini-2.0-flash

    addressing you directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     himself
    -0.51
     themselves
    -0.50
    iconque
    -0.48
    himself
    -0.47
     jLabel
    -0.47
    Downloaded
    -0.46
    */),
    -0.45
     Jub
    -0.44
     Himself
    -0.43
     pháp
    -0.43
    POSITIVE LOGITS
    Your
    0.93
     your
    0.89
    your
    0.88
     Your
    0.88
     youre
    0.81
     you
    0.81
    you
    0.78
    Ваш
    0.77
     YOUR
    0.76
    You
    0.76
    Act Density 0.129%

    No Known Activations