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

    Neuronpedia

    INDEX
    Explanations

    expressions related to personal experience and feedback

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

    First-person perspective or personal opinions

    np_acts-logits-general · gemini-2.0-flash

    first-person pronouns and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.56
    NameInMap
    -0.56
     intptr
    -0.52
     CURIAM
    -0.51
     ContentValues
    -0.48
    قایناق‌لار
    -0.47
    ----</
    -0.47
     lives
    -0.43
     CharSequence
    -0.41
     Proper
    -0.40
    POSITIVE LOGITS
     myself
    1.05
    myself
    0.86
     Myself
    0.80
    Myself
    0.78
     my
    0.77
     meine
    0.74
     mijn
    0.73
     meinem
    0.67
     meiner
    0.66
    我的
    0.66
    Act Density 0.744%

    No Known Activations