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

    Neuronpedia

    INDEX
    Explanations

    positive descriptors and features associated with objects or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     strto
    -0.47
     contextLoads
    -0.43
     estr
    -0.40
    MockBean
    -0.39
    طلحات
    -0.37
    RotationOrder
    -0.35
     radioButton
    -0.35
    ushka
    -0.34
     تضيفلها
    -0.34
    fara
    -0.34
    POSITIVE LOGITS
     cool
    2.36
     Cool
    1.77
    cool
    1.73
     nice
    1.72
     COOL
    1.70
    Cool
    1.69
     coolest
    1.59
     awesome
    1.55
     neat
    1.51
    COOL
    1.49
    Act Density 0.411%

    No Known Activations