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

    Neuronpedia

    INDEX
    Explanations

    expressions of positivity and satisfaction in experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complexType
    -0.56
    onAttach
    -0.56
    ConstraintMaker
    -0.54
     likely
    -0.54
     TestBed
    -0.54
     autorytatywna
    -0.52
    RectangleBorder
    -0.51
    likely
    -0.50
     копия
    -0.49
     onCancelled
    -0.49
    POSITIVE LOGITS
    Прият
    0.61
    HideFlags
    0.59
    Хро
    0.58
     thú
    0.56
    freude
    0.55
    reszcie
    0.55
    astie
    0.54
     ride
    0.53
    omeness
    0.53
    ocardio
    0.52
    Act Density 0.219%

    No Known Activations