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

    Neuronpedia

    INDEX
    Explanations

    references to choice and commitment in relationships

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

    people who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    -0.37
     surprise
    -0.35
     was
    -0.35
    gameObject
    -0.35
     pretty
    -0.35
     auszu
    -0.34
     itself
    -0.33
    let
    -0.33
    pedia
    -0.33
    pus
    -0.33
    POSITIVE LOGITS
     którzy
    0.71
     Normdatei
    0.69
    Controllo
    0.63
    Personendaten
    0.61
     queſta
    0.60
     betweenstory
    0.60
    UVWXYZ
    0.59
     kteří
    0.59
     ktorí
    0.59
    UIControlState
    0.58
    Act Density 0.113%

    No Known Activations