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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and backgrounds

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

    following pronouns (she, he, I)

    np_acts-logits-general · gemini-2.0-flash

    personal pronouns performing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     existencia
    -0.57
     existence
    -0.57
     EXIST
    -0.53
    Existence
    -0.50
     existed
    -0.50
     tratt
    -0.49
    existence
    -0.48
     bä
    -0.48
     exists
    -0.47
    obe
    -0.47
    POSITIVE LOGITS
     developed
    0.76
     found
    0.73
     branched
    0.69
     discovered
    0.68
     constater
    0.66
     develop
    0.65
     learned
    0.65
     gained
    0.64
    DockStyle
    0.63
     remar
    0.63
    Act Density 0.268%

    No Known Activations